Commit context — which agent session made this change?
Trace a file, function, or line back to the agent session and commit that produced it — with strict anti-fabrication rules
- What
- Trace a file, function, or line back to the agent session and commit that produced it — with strict anti-fabrication rules
- Cost
- Free
- Needs
- the AgentMemory MCP/tools (memory_commit_lookup, memory_recall) available in your agent environment; a git repo with agent-linked commits; no accounts or API keys needed.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a code-archaeology skill by @rohitg00 that answers "why is this code here" and "what was the agent doing when this changed" for agent-built codebases: find the SHA via `git blame` / `git log`, look it up through the AgentMemory tooling (`memory_commit_lookup`, `memory_recall`), and present the commit plus the linked session(s) with importance-filtered observations. Its defining feature is honesty under uncertainty — when a lookup returns `commit: null`, the skill reports "this commit predates session linking, so there is no recorded agent session" and never narrates intent from the diff alone. Includes a checklist (SHA comes from git, never guessed; session details quoted verbatim) and links to sibling skills (`commit-history`, `recall`). Honest caveats: it only works where the AgentMemory MCP/tools are actually installed and available to the agent; sessions must have been recorded — older commits return null by design, not by failure. Credit to its creator. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Commit context — which agent session made this change? is a free Muse skill that traces a file, function, or line back to the agent session and commit that produced it, using git blame, git log, and AgentMemory lookups, with strict anti-fabrication rules. When no session is linked, it says so honestly instead of narrating intent from the diff.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit df3d4a8Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: the AgentMemory MCP/tools (memory_commit_lookup, memory_recall) available in your agent environment; a git repo with agent-linked commits; no accounts or API keys needed. Install "Commit context — which agent session made this change?" for me. It's a code-archaeology skill: find a commit SHA via git blame/log, look it up through AgentMemory, and present the commit plus its linked agent session(s) — with strict rules to never fabricate intent when no session is recorded. Repository: https://raw.githubusercontent.com/rohitg00/agentmemory/df3d4a83b966d8d415cb9180d5a4724b07f729dc/plugin/skills/commit-context/SKILL.md Pinned version: install the code at commit df3d4a83b966d8d415cb9180d5a4724b07f729dc exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "commit-context". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. save my API key in the vault). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- df3d4a8 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.