Cmd Session Commit
Capture learnings from the current coding session and update AGENTS.md. Use when the user asks to close the loop, run session-commit, record best practices, or update agent instructions based on recent work.
Install
$ agentstack add skill-olshansk-agent-skills-cmd-session-commit ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-olshansk-agent-skills-cmd-session-commit) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Session Commit
Analyze the current coding session, propose improvements to AGENTS.md, and apply approved changes.
Workflow
- Read the current
AGENTS.mdand build a mental map of existing sections. - If the repo documents a validation or repair command for instruction files, run it before proposing edits.
- Extract only durable learnings from the current session.
- Propose changes using the format in
references/change-proposal-format.md. - Wait for explicit user approval before applying any edits.
- Apply approved changes and merge with existing content.
What to capture
- Coding patterns and conventions established in the session
- Architecture decisions and reasoning that should persist
- Debugging playbooks and recurring gotchas
- Workflow preferences that improve future sessions
Guardrails
- Do not capture transient implementation details that will age quickly.
- Prefer updating existing sections before creating new headings.
- Use concise bullet points rather than long paragraphs.
- Keep guidance tool-agnostic unless behavior differs by tool.
- If no meaningful learning occurred, report that and stop.
Pointer file behavior
If CLAUDE.md, CODEX.md, or GEMINI.md are missing or empty, create symlinks that point to AGENTS.md.
Output contract
- Proposal stage: output only proposed changes with explicit add/modify/remove counts.
- Apply stage: update
AGENTS.mdonly after explicit approval. - Completion stage: summarize what changed and where.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Olshansk
- Source: Olshansk/agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.