Sponsio

Sponsio — Agent Safety Lifecycle Companion

Sponsio is a Python/TypeScript runtime safety layer for LLM agents: it evaluates deterministic contracts against each tool call and can block (enforce) or just log (observe) violations. The engine is deterministic-only. This skill covers the full lifecycle — first-time setup, contract authoring/review, observe-mode tuning, and flipping to enforce — by orchestrating Sponsio's CLI and explaining its output in plain language.

This skill does NOT reimplement Sponsio's logic; it calls the CLI and interprets results.

When to use this skill

Dispatch by what the user is trying to do. Pick ONE workflow and follow it; do not run multiple workflows in one turn.

| User is… | → Workflow | |---|---| | Setting up Sponsio for the first time in a project ("add sponsio", "install sponsio", "add guardrails") | W1 — Initial setup (just dispatch `sponsio init) | | Handing you a codebase and asking "what could go wrong?" / wants a fresh contract file from scratch / has a policy doc to encode | **W2 — Audit & refine** | | Authoring contracts for a Claude Code / OpenClaw plugin or a bare MCP server (input is a plugin manifest, not source code) | **W2b — Plugin / MCP contracts** | | Tightening rules that apply to Task-spawned subagents (Cursor / Claude Code) — they lack user context and need stricter privileges than the main agent | **W2c — Subagent privilege boundary** | | Tuning the IDE's OWN host-plugin library (Claude Code's Bash / Read / Write / MCP gating; Cursor likewise) — different from the user's project sponsio.yaml | hand off to the sponsio-claude-code:configure` skill (or the cursor analog). Don't reimplement here. | | Has Sponsio running in observe mode and wants to review violations, tune thresholds, silence false positives | W3 — Tune in observe | | Ready to ship — wants to move from observe to enforce, needs regression confidence | W4 — Flip to enforce | | Sponsio errored, a rule isn't firing when it should, a rule is firing when it shouldn't | W5 — Troubleshoot |

Do NOT trigger for: general LLM-safety discussions not tied to a specific codebase; non-agent code review (linting, correctness).

Prerequisites (run silently before any workflow)

sponsio --version

• Not found → install: pip install sponsio (or pip install -e ".[all]" from a local clone).
• For --llm inference, check: OPENAI_API_KEY / ANTHROPIC_API_KEY / GEMINI_API_KEY / GOOGLE_API_KEY. Absent → still proceed; AST-based extraction and all of W3/W4/W5 work with zero keys.

---

Editing contract YAML — write rules by file

Sponsio contract YAMLs split into two trust zones with different write rules. Pick the right zone before any edit; the runtime's self-modify pack enforces the host-zone rules, but cross-zone slips are still a config-correctness bug we'd rather avoid up-front.

Zone A — project YAML (you may add additively)

Path: /sponsio.yaml — the file sponsio onboard writes into the user's repo. This evolves through every onboard / scan cycle. Adding new contracts via Edit (extending old_string) is the supported workflow.

Three legal write modes:

1. Add a new contract — Edit with new_string extending

old_string (the invariant: old_string ⊆ new_string):

``text old_string = the verbatim tail of the existing file ending at the last contract entry (or the last contracts: line if the list is empty) new_string = old_string + "\n - " ``

1. Tune an existing pack-shipped rule — never edit the rule

directly; append a customized: entry:

```yaml customized:

• match: { desc: "" }

A: "" # to relax # or args: [...] # to retune thresholds # or disabled: true # to silence (last resort) ```

1. Run sponsio scan for bulk additions from code / policy,

merges additively and writes atomically:

``bash sponsio scan -o ./sponsio.yaml --append ``

Zone B — host bucket + plugin bundle YAMLs (user-only — never write directly)

Paths:

• ~/.sponsio/plugins/{{HOST_BUCKET}}/sponsio.yaml (this host's runtime library)
• ~/.sponsio/plugins/{{HOST_BUCKET_SUBAGENT}}/sponsio.yaml (this host's subagent library)
• ~/.sponsio/plugins//sponsio.yaml (per-plugin / per-MCP-server bundle — github, filesystem, my-plugin, …)

These files govern your own future tool calls. The runtime self-modify pack blocks every Edit / Write / MultiEdit you'd attempt against them — for the host bucket because rewriting your own rules is privilege escalation, and for the per-plugin bundles for the same reason (they constrain the plugin tools you'll call later). The {{HOST_BUCKET}} placeholders above are baked in at skill install time (_host_cursor, _host_claude_code, _host_openclaw, …) so each host only loses write access to its own bucket.

You must NOT use Edit, Write, MultiEdit, or Bash with shell redirects (>, >>, tee, sed -i, cp, mv, rm, dd) on any path under ~/.sponsio/plugins/. The legitimate update paths are:

• CLI (you can run via Bash):

``bash sponsio plugin install # copy a fresh bundled starter sponsio plugin scan --apply # regenerate per-plugin bundle sponsio plugin show # surface what's loaded ``

• Hand-edit by the user in their text editor.

For customizations the user agreed to during a tuning conversation, do NOT ghostwrite the YAML they should paste. Contract content in Zone B has exactly four legitimate sources: bundle libraries (sponsio plugin install), CLI extraction (sponsio plugin scan, sponsio scan, sponsio onboard), the user's own keystrokes, and customized: blocks the user authors themselves. An LLM-composed snippet has none of those provenances — it's configuration with no audit trail.

The flow:

1. Restate the user's intent in plain English and identify the

shipped rule it affects. sponsio plugin show prints the desc: of every loaded rule; quote a desc verbatim from that output if you need to refer to one — do NOT compose YAML around it.

1. Tell the user the file path and describe the change in words

("add a customized: entry beside contracts: whose match.desc matches the rule you want to silence, with disabled: true"). Point them at the existing pack's syntax for reference. Let them write the YAML themselves.

1. When they say they're done, run

sponsio validate --config ~/.sponsio/plugins//sponsio.yaml and help debug if it doesn't parse.

Forbidden write modes (universal)

• Write on any contract YAML above — overwrites the whole

file in one go; bypasses the additive evidence even when the result happens to be a superset.

• Edit on a Zone-B path — denied by the self-modify pack

regardless of additive intent.

• **Edit on a Zone-A path where new_string does NOT contain

old_string** — a modification or deletion masquerading as an edit; treat as forbidden.

• MultiEdit on any contract YAML — same shape as Write.
• Bash with shell write operators (>, >>, tee,

sed -i, cp, mv, rm, dd) targeting any of these paths — the runtime blocks Zone B; treat Zone A the same way.

Why this matters

The user's invariant: adding contracts is always allowed; modifying or deleting existing ones is not. Following this protocol makes that invariant easy to see at the diff level (old_string ⊆ new_string). When the user audits your edits later, "was anything removed or changed?" reduces to a string-containment check.

If you genuinely need to remove a rule

You don't. Use customized: ... disabled: true (an additive edit that silences the rule) or ask the user to delete it by hand. The agent never has authority to remove its own contracts.

Pattern generality — match operator intent, not demo data

When the operator's NL says "block public gists" or "cap files at 3", write the rule against the operator's literal intent. Do not infer file extensions, content types, naming conventions, or path structures from sample data, demo fixtures, or examples you've seen — unless the operator explicitly named them.

Concrete: a regex like (\.md"\s*:.*?){4,} matches only keys ending in .md, which means a 4-file gist of .json / .txt / .csv / extension-less keys passes freely. If the operator said "cap files at 3", the right form is (\".+?\"\s*:\s*\{){4,} — any 4+ keys. Same principle for path globs (/work/notes/.*\.md vs /work/notes/.+), arg_field_has value patterns, and match: selectors.

If the operator's intent IS demo-specific ("block any .md dump from this notes plugin"), keep the narrow pattern but record the assumption in the contract desc: so a later reviewer sees the constraint instead of inferring a bug.

The flip side — don't broaden past what the operator named

The operator's NL also has a verb scope. When a policy says "no destructive verbs against AWS" the agent must not emit \baws\s+ (matches every aws invocation including aws s3 ls / aws sts get-caller-identity). The regex must require both the provider and a destructive-verb token from the policy.

Concrete:

| Policy phrase | Wrong (overbroad) | Right (verb-anchored) | |---|---|---| | "no destructive AWS calls" | \baws\s+ | \baws\s+(rds\|s3api\|ec2)\s+(delete-\|terminate-)\w+\b | | "no destructive gcloud calls" | \bgcloud\s+ | \bgcloud\s+\w+\s+(delete\|destroy\|drain)\b | | "no destructive Railway control plane" | api\.railway\.app | (curl\|http\|wget)[^\|;&]*-X\s+DELETE[^\|;&]*\bapi\.railway\.app\b | | "no DROP TABLE" | DROP | \bDROP\s+TABLE\b |

The shipped packs already follow this convention (see sponsio:incident/cursor-railway-wipe). When you extract from a policy doc, mirror the pack style: every command-shape regex is (host or tool prefix) AND (destructive verb the operator named). Bare provider prefixes are false-positive factories — every routine aws s3 ls in a CI script becomes a violation.

If the operator named providers exhaustively in prose ("Railway, Fly, Render, Supabase, Vercel, Cloudflare, Heroku, AWS, GCP"), keep all named providers, each anchored to its own verb set. Do not collapse them into a single broad alternation that drops the verb anchor.

---

W1 — Initial setup

Goal: from "project has no Sponsio" to "agent runs under observe mode with a sane contract file".

The CLI now has a one-shot wizard that covers the common path — detect framework + IDEs, ask which to install, dispatch `sponsio onboard / sponsio host install / sponsio skill install` accordingly, then verify. W1 is just orchestrating that wizard, not reimplementing it.

Steps

1. Run the wizard.

``bash sponsio init # interactive TTY sponsio init --apply 'framework=;ides=:,...;mode=observe' # non-interactive ``

Picks string format:

• `framework=. none` is "bare loop, generic

`guard.guard_before/after wiring"; an empty framework=` skips the onboard step entirely.

• `ides=:,... per-IDE pick. ``` is

`none / skill (drop SKILL.md only) / full` (host hooks + SKILL.md, the canonical "protect this IDE" pick).

• `mode=observe|enforce`. Default observe; enforce flips

are W4's job.

Use `sponsio init --plan '' first to surface the exact commands the wizard will run, especially when you're non-interactive. Surface sponsio init`'s output to the user verbatim — the panel + preview + recap blocks are designed to be readable as-is.

1. Patch the agent entry file (only when `framework ≠ ""`).

``bash sponsio onboard . --emit-context > /tmp/sponsio-onboard-context.json ``

Read the JSON. Pick the entry file in this priority:

1. `entry_file_candidates` has exactly one strong match.
2. Else dedupe `tool_inventory[*].filepath` — one file, use it.
3. Else stop and ask the user.

If the file already imports `from sponsio. (Python) or from "@sponsio/sdk" (TS), it's already wrapped — skip. Otherwise splice wrap_snippet from the JSON: imports + guard construction at the top, wrap site adapted to the file's actual idiom (canonical create_react_agent(model, guard.wrap(tools)) if present, else adapt — e.g. tools_by_name = guard.wrap(TOOLS).tools_by_name` for a name-keyed dispatch loop). Show the diff before writing.

1. Verify.

``bash sponsio doctor sponsio validate --config sponsio.yaml ``

Surface every warning / fail line verbatim. If `sponsio doctor` FAILED (not warned, failed), stop here — don't let the user run their agent thinking the install is healthy when it isn't.

1. Explain observe mode explicitly: "Nothing is blocked on day 1.

Every contract is still evaluated; violations are logged to `~/.sponsio/sessions//*.jsonl. Use sponsio report --since 24h` after a day of real traffic to see what would have been blocked. When you're ready to flip, that's W4."

Beyond W1 — pointers

Onboarding is just install + wire + verify. These are SEPARATE workflows, not extensions of W1:

• Author tighter contracts from a policy doc / threat model /

actually-scanned codebase → W2 (audit & refine).

• Tune host-plugin libraries (Bash / Read / Write / MCP gating

in this Claude Code or Cursor session) → invoke the `sponsio-claude-code:configure skill (or the cursor analog). That skill owns sponsio plugin scan / sponsio plugin append` / per-MCP-server library generation. W1 doesn't duplicate it.

• Move from observe to enforce → W4.
• Something doesn't fire / fires wrong → W5.

Choosing the write target — Zone A vs Zone B

`sponsio init`'s axes already encode the destination decision:

• Axis 1 (framework wrap, picked at non-empty / non-`none`)

→ writes `/sponsio.yaml. This is **Zone A** — governs the LLM agent the user is wiring Sponsio INTO. You may Edit/Write this file; sponsio validate --config ` after.

• Axis 2 (per-IDE level=full) → writes

`~/.sponsio/plugins/_host_/sponsio.yaml via sponsio host install. This is **Zone B** — governs the HOST agent (i.e. you, Claude Code / Cursor). Edit/Write/ MultiEdit are denied by the self-modify pack; the only way to extend it from inside the host is sponsio plugin append`.

If a user later asks you to add rules and the destination is ambiguous (project rules vs host-IDE rules), ask:

> "These rules — should they govern (a) the LLM agent your project > deploys (Zone A: `/sponsio.yaml), or (b) my own tool > calls inside this IDE (Zone B: ~/.sponsio/plugins/_host_/ > sponsio.yaml`)?"

Two destinations need two files; conflating them silently breaks one or both.

Adding rules to Zone B (host bucket) — sponsio plugin append

When a Zone-B addition is the right call, you can't Edit/Write the host yaml directly. Use the append CLI:

# 1. Write the new rules to a staging file OUTSIDE Zone B (project
#    root is fine).  Never name it sponsio.yaml — collides with
#    project-config.
sponsio plugin append --from  --target  --dry-run
sponsio plugin append --from  --target 
rm      # delete after success

`plugin append is structurally additive: it rejects anything beyond contracts: entries — no customized:, no disabled:`, no desc collisions, no top-level keys. Tell the user up front you'll be running this on their behalf so they're not surprised when it appears.

Auto-selected packs

`sponsio onboa

…

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: SponsioLabs
• Source: SponsioLabs/Sponsio
• License: Apache-2.0
• Homepage: https://sponsio.dev/

Install and usage instructions live in the source repository linked above.