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-repo-behavior-spec-loopWrote 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-repo-behavior-spec-loop)<a href="https://agentmods.dev/skills/jakyeamos/tmcp/tmcp-repo-behavior-spec-loop"><img src="https://agentmods.dev/badge/skills/jakyeamos/tmcp/tmcp-repo-behavior-spec-loop/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-repo-behavior-spec-loop"><img src="https://agentmods.dev/badge/skills/jakyeamos/tmcp/tmcp-repo-behavior-spec-loop.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 | $0.00000 | $0.00583 |
| Opus 5 | $0.00000 | $0.00292 |
| Sonnet 5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
tmcp-repo-behavior-spec-loop 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TMCP Repo Behavior Spec Loop
Status: experimental. This workflow remains shipped and callable, but its public contract may change.
Use this skill when the user asks to inventory every feature from code, create or maintain a canonical behavior spreadsheet, test user stories against the running app, fix defects, re-test, add regression coverage, and drive a repo to an evidence-backed known-good state.
Do not use it for a narrow bug fix, a generic test-strategy review, or a release-readiness audit unless the user specifically wants the full behavior spreadsheet and verification loop.
Workflow
- Gather evidence: repo instructions, routes/pages/layouts, components, APIs, server actions, auth and permissions, forms, modals, search/filter/sort/pagination, data models, jobs, tests, scripts, and dev workflow.
- Invoke
tmcp_harvest_skillsortmcp_recommend_workflowswithcandidate_workflows: ["repo_behavior_spec_loop"]. - Build or update exactly one canonical spreadsheet with stable
AREA-###Feature IDs, source file/function citations, expected behavior from code, user-acceptable behavior, test method, observed behavior, status, defect metadata, evidence, iteration, and last tested commit. - Use
expert_rubric_review_planfor the scored workflow packet and evidence audit before implementation-heavy remediation. - Test each row with the strongest available method, fix defects with the smallest safe change, re-test, and add regression coverage or an explicit manual-only reason.
- Stop only for destructive actions, real product decisions, unavailable required input, or the safety cap after repeated failed fix/re-test attempts.
If MCP tools are unavailable, run from the TMCP plugin root:
node scripts/tmcp_launcher.mjs recommend "<project-path>" --candidate-workflows repo_behavior_spec_loop --min-confidence 0.1 --write-artifacts
Output Contract
Produce or cite:
- TMCP packet and
substance_check. - Canonical behavior spreadsheet path and current commit.
- Coverage audit for discovered feature rows and source citations.
- Status counts across
Discovered,Spec'd,Test-Blocked,Tested-Pass,Tested-Fail,Fixing,Fixed,Verified, andRegression-Covered. - Defects by type, root cause, fix summary, and evidence.
- Verification commands or browser actions, observed results, iteration, and last tested commit.
- Regression coverage added or explicit manual-only reason.
- Complexity-gate review and unresolved product/environment questions.
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 · 42 lines · 0 tokens per session scan A 30540b5d971a
tmcp-repo-behavior-spec-loop is a skill published in the GitHub repository jakyeamos/tmcp (0 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 583 tokens. 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
typescript-providers
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.
test-case-report-builder
A workflow for creating project test cases and formal test reports, including Excel test-case files and Word documents. It can also summarize automated test results and preserve reusable testing documentation.
python-pro
Use when building Python 3.11+ applications requiring type safety, async programming, or robust error handling. Generates type-annotated Python code, configures mypy in strict mode, writes pytest test suites with fixtures and mocking, and validates code with black and ruff. Invoke for type hints, async/await patterns…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.