AgentStack
SKILL verified MIT Self-run

Context Dump

skill-bnet47-codexicon-context-dump · by bnet47

Create or resume an explicit human-readable checkpoint across compaction, sessions, or handoff. Primary agent only.

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-bnet47-codexicon-context-dump

✓ 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-bnet47-codexicon-context-dump)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2d ago

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 Context Dump? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Context checkpoint

Create or resume a concise checkpoint without transcript archaeology. Semantic checkpoints are explicit project writes; hooks never create or commit them automatically.

1. Choose the branch

  • For a checkpoint or handoff request, continue with Create.
  • For a resume or continuation request, continue with Resume.

2. Create

Inspect the active request/spec/plan, current diff or changed files, latest verification, and blockers. Do not copy secrets, large logs, transcript content, or code that already exists in tracked files.

Run the repository manager from the root:

python scripts/codexicon.py checkpoint --slug [short-slug] --title "[short title]" --summary "[working, partial, and broken state]" --resume-note "[minimum critical continuation context]" --next "[immediate concrete action]" --related [relative spec or plan path] --verification "[exact command — result and time]" --blocker "[blocker and required input]" --decision "[decision and rationale]"

Repeat --next, --related, --verification, --blocker, and --decision as needed. Omit optional categories that are empty. Quote values for the active shell; never interpolate command output or untrusted text into the command.

The manager validates related paths, captures only dirty path names plus Git identity, and atomically writes agent_docs/sessions/[YYYY-MM-DD]-[slug].md. It refuses an existing filename. Do not hand-edit the first metadata line.

3. Resume

Run:

python scripts/codexicon.py resume
python scripts/codexicon.py doctor

Use the newest repository-compatible checkpoint as orientation, then verify its HEAD, related paths, current diff, and verification claims before acting. A checkpoint is evidence, not authority to discard later user changes or repeat external side effects.

If no compatible checkpoint exists, inspect the latest plan and current diff directly; do not select a checkpoint from a different clone by filename alone.

4. Keep durable and ephemeral guidance separate

Do not place session state in AGENTS.md; it is always-loaded repository guidance. .codex-state/ remains local verification state, not project memory. Do not require an MCP memory service. If the user explicitly wants cross-project memory, store only the compact resume note.

Do not commit or push the checkpoint unless the user asks to ship or explicitly requests a checkpoint commit.

Source & license

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

  • Author: bnet47
  • Source: bnet47/codexicon
  • License: MIT
  • Homepage: https://bnet47.github.io/codexicon/repo-template-playbook.html

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.