Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/fmagent-project/fm-agent-plugin/exportnpx skills add fmagent-project/FM-Agent-Plugin --skill exportgit clone --depth 1 https://github.com/fmagent-project/FM-Agent-PluginWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00101 | $0.01211 |
| Opus 5 | $0.00051 | $0.00606 |
| Sonnet 5 | $0.00020 | $0.00242 |
| Haiku 4.5 | $0.00010 | $0.00121 |
Grade A, and why
FM-Agent-Export scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Export the conversation to ./fm_agent_plugin/ after a git commit is executed as a Bash command. Two output files are created: a full transcript and a summary.
Overview
This skill runs automatically after any git commit Bash command completes. It captures:
- The commit metadata (hash, message, author, changed files)
- The conversation turns between the previous commit and the new commit
- A concise summary of the user's goal, decisions made, and code changes
Output files use the commit hash as identifier and are written to the current project directory where Claude Code or codex is running (not the plugin directory): export-<COMMIT_ID>.md and export-<COMMIT_ID>-summary.md in the ./fm_agent_plugin/ subdirectory.
If no git commit has been executed in the current session, do NOT run this skill — return a message saying there's no commit to export to.
IMPORTANT — Multiple commits in session: If multiple git commit Bash commands have been executed in the current session, run this skill AFTER EACH COMMIT. For each commit, export the conversation between that commit and the one before it. The most recent commit is always git rev-parse --short HEAD, the previous one is HEAD~1.
Steps
1. Get the commit id
This skill triggers after a git commit Bash command. Extract the commit hash using:
git rev-parse --short HEAD
Determine whether this is the first git commit Bash command in the current session by checking the current session context for any earlier successful git commit Bash command before the one that just finished.
- If no earlier successful
git commitBash command appears in the current session context, this is the first commit in the current session. There is no earlier in-session commit boundary. Use the session start as the previous reference, meaning the beginning of the current conversation in this session. Scope the export to all conversation turns from session start up to this commit. - If this is not the first commit in the current session, get the previous commit hash for scoping the conversation:
git rev-parse --short HEAD~1
Use that previous in-session commit as the earlier boundary for the export.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 120 lines · 101 tokens per session scan A b2fd86afc08a
FM-Agent-Export is a skill published in the GitHub repository fmagent-project/FM-Agent-Plugin (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,211 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.