AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Agent Scope Lock

skill-graysurf-agent-kit-agent-scope-lock · by graysurf

Create, read, validate, and clear edit-scope locks through the nils-cli agent-scope-lock command.

No reviews yet
0 installs
6 views
0.0% view→install

Install

$ agentstack add skill-graysurf-agent-kit-agent-scope-lock

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-graysurf-agent-kit-agent-scope-lock)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
Archived

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Agent Scope Lock? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Agent Scope Lock

Use this skill when an agent workflow needs a mechanical edit boundary before changing files.

Contract

Prereqs:

  • Run inside the target git work tree.
  • git available on PATH.
  • Released usage: agent-scope-lock available on PATH from nils-cli 0.8.4 or newer.
  • Local checkout fallback usage: Rust/Cargo plus a validated local nils-cli checkout that builds the

nils-agent-scope-lock package when PATH is absent or too old.

  • Scope paths are repository-relative paths chosen by the owning workflow or agent.

Inputs:

  • create: one or more --path flags, optional --owner , optional --note , and optional

--format json.

  • read: optional --format json.
  • validate: required --changes all|staged|unstaged, and optional --format json.
  • clear: no required inputs.

Outputs:

  • agent-scope-lock create: writes the git metadata lock file resolved by git rev-parse --git-path agent-scope-lock.json.
  • agent-scope-lock read: prints the current lock state.
  • agent-scope-lock validate: reports whether selected working-tree changes stay inside the lock scope.
  • agent-scope-lock clear: removes the current lock file.
  • No skill-local lock file, parser, or artifact format; treat the nils-cli command as the only stable contract.

Exit codes:

  • 0: command succeeded.
  • non-zero: usage, git/repository, lock-state, validation, or dependency failure from agent-scope-lock.

Failure modes:

  • agent-scope-lock is unavailable on PATH and no validated local checkout invocation is being used.
  • Current directory is not inside the intended git work tree.
  • Requested create paths are not repository-relative or do not match the intended edit boundary.
  • validate finds changes outside the active lock scope.
  • Caller mixes a local checkout fallback with a different released PATH binary; rerun with one explicit invocation source.

Setup

Released PATH boundary:

agent-scope-lock --help

Use the PATH command after installing nils-cli 0.8.4 or newer with nils-agent-scope-lock on PATH.

Local checkout fallback boundary:

cargo run --locked --manifest-path "$HOME/Project/sympoies/nils-cli/Cargo.toml" \
  -p nils-agent-scope-lock --bin agent-scope-lock -- --help

Run the Cargo form from the target git work tree, not from the nils-cli checkout. Use it only when PATH is absent or reports an older nils-cli. Keep the same agent-scope-lock subcommands and flags in both modes.

Commands (only entrypoints)

Released PATH command:

agent-scope-lock create --path  [--path  ...] [--owner ] [--note ] [--format json]
agent-scope-lock read [--format json]
agent-scope-lock validate --changes all|staged|unstaged [--format json]
agent-scope-lock clear

Local checkout fallback command:

cargo run --locked --manifest-path /path/to/nils-cli/Cargo.toml \
  -p nils-agent-scope-lock --bin agent-scope-lock --  ...

Do not edit agent-scope-lock.json manually or duplicate scope validation logic in skill scripts.

Workflow

  1. Before editing, create the narrowest practical lock:

agent-scope-lock create --path [--path ...] --owner --note --format json

  1. Before acting on an existing task, read the current lock:

agent-scope-lock read --format json

  1. Before reporting completion, staging, committing, or handing off, validate:

agent-scope-lock validate --changes all --format json

  1. Clear the lock only when the owning workflow has completed or explicitly hands off:

agent-scope-lock clear

  1. On failure, report the exact command, exit code, stdout, and stderr; do not claim the edit scope is valid.

References

  • docs/runbooks/skills/TOOLING_INDEX_V2.md

Source & license

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

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

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.