Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jakyeamos/tmcpnpx agentmods add skills/jakyeamos/tmcp/tmcp-skill-harvestWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jakyeamos/tmcp/tmcp-skill-harvest)<a href="https://agentmods.dev/skills/jakyeamos/tmcp/tmcp-skill-harvest"><img src="https://agentmods.dev/badge/skills/jakyeamos/tmcp/tmcp-skill-harvest/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jakyeamos/tmcp/tmcp-skill-harvest"><img src="https://agentmods.dev/badge/skills/jakyeamos/tmcp/tmcp-skill-harvest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00039 | $0.00414 |
| Opus 5 | $0.00019 | $0.00207 |
| Sonnet 5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
tmcp-skill-harvest 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 11d 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.
What it actually says
TMCP Skill Harvest
Status: stable as a skill package. The tmcp_harvest_skills MCP tool is experimental, so its tool contract may evolve independently.
Use this skill when the user asks to harvest skills, extract reusable agent behavior, compile a skill packet, inspect local instructions, turn process docs into reusable workflow material, or compare behavior across skill/rule files.
This is a discovery and packet-compilation workflow. Do not use it for direct feature implementation unless the user explicitly asks to apply the harvested packet.
Workflow
- Identify the smallest useful source set:
SKILL.md,AGENTS.md,CLAUDE.md,.cursor/rules,.github,README.md,docs,planning,workflows, and relevant markdown process docs. - Invoke TMCP through MCP tools when exposed:
tmcp_harvest_skillsfor source nodes, behavior atoms, redaction summaries, warnings, and packet seed.tmcp_explainwhen a task-specific packet is also needed.
- If MCP tools are not exposed, use the CLI from the TMCP plugin root:
node scripts/tmcp_launcher.mjs harvest "<source-path>" --objective "Harvest reusable skill behavior" --write-artifacts
- Preserve redaction behavior and report warnings as evidence, including any
skill_eval_advisoriessurfaced by the evaluation anti-pattern catalog. - Keep the packet focused; avoid sweeping unrelated docs into the harvest.
Output Contract
Produce or cite:
- Harvest source paths and skipped/missing-source warnings.
- Redaction summary.
- Behavior atoms and source tiers.
- Skill evaluation advisories when anti-patterns are detected.
- Packet seed and recommended next use.
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.
- 11d ago First seen · 39 lines · 39 tokens per session scan A d57d72391771
tmcp-skill-harvest is a skill published in the GitHub repository jakyeamos/tmcp (0 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 414 once invoked, about $0.0002 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
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
composio
Route and complete Composio work across Composio For You and Composio Platform. Use when the user mentions Composio; wants an agent to use apps such as Gmail, Slack, GitHub, Notion, Calendar, or Linear; needs first-time setup, an SDK or MCP integration, CLI operation, migration guidance, current documentation, or help…
live-tutorial
Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application. Use when asked for a tutorial video, not merely to watch an action live.
docs-decisions
Work on Composio documentation content, Fumadocs configuration, changelogs, docs automation prompts, docs decisions, ADR-style records, and docs review guidance. Use for files under docs/, documentation workflows, or requests to record or update a docs decision. Do not use for SDK runtime changes unless docs are the…
repo-guidance
Navigate the Composio SDK monorepo, branch and PR workflow, repo layout, generated-file boundaries, changesets, and shared maintenance rules. Use when work spans multiple packages, when deciding where code belongs, when preparing a PR, or when the user asks about repository conventions rather than a specific SDK…
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.