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 skills add babyworm/rtl-agent-team --skill rtl-p5s-coverage-policygit clone --depth 1 https://github.com/babyworm/rtl-agent-teamWrote 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/babyworm/rtl-agent-team/rtl-p5s-coverage-policy)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/rtl-p5s-coverage-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-p5s-coverage-policy/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/babyworm/rtl-agent-team/rtl-p5s-coverage-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-p5s-coverage-policy.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 | $0.00025 | $0.02719 |
| Opus 5.5 | $0.00010 | $0.01088 |
| Sonnet 5.5 | $0.00005 | $0.00544 |
| Haiku 4.5 | $0.00003 | $0.00272 |
Grade A, and why
rtl-p5s-coverage-policy 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 20d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coverage Analysis Policy
Coverage Targets
| Metric | Target | Evaluated On |
|---|---|---|
| Line coverage | ≥ 90% | Post-exclusion |
| Toggle coverage | ≥ 80% | Post-exclusion |
| FSM coverage | ≥ 70% | Post-exclusion |
Raw coverage is always reported alongside post-exclusion numbers for transparency.
Coverpoint Iterative Refinement (minimum 3 rounds)
Coverage coverpoint extraction and test generation must iterate at least 3 times:
- Round 1 (Initial Analysis): Identify all uncovered lines, branches, FSM states/transitions. Prioritize gaps (HIGH/MED/LOW). Generate first batch of directed tests for HIGH gaps.
- Round 2 (Deepen): Re-analyze coverage after Round 1 tests. Identify newly reachable but still uncovered paths. Add cross-coverage points (e.g., cmd × size, state × error). Target MED gaps. Check for unreachable code (waiver candidates).
- Round 3 (Close): Final coverage push. Add corner-case stimulus for remaining gaps. Verify coverage targets met (line ≥ 90%, toggle ≥ 80%, FSM ≥ 70%). Document waived bins with justification.
- Additional rounds: Continue until coverage targets are met or all remaining gaps are justified as waived.
Each round produces a progress note at .rat/scratch/phase-5/coverage-iteration-r{N}.md.
Escalation & Stop Conditions
- LOW priority gaps flagged as unreachable → report to user, recommend dead code removal
- Coverage tool format unrecognized → halt, ask user for coverage format (Icarus, VCS, etc.)
- Coverage below 70% after gap fill → escalate to rtl-architect for structural review
Final Checklist
- sim/coverage/coverage_gaps.md written with all gaps prioritized
- New tests written for all HIGH priority gaps
- Coverage improvement measured and reported
- Unreachable code gaps flagged separately
CDTG Feedback Protocol (Coverage → Testbench-Dev)
When coverage-analyst identifies HIGH/CRITICAL gaps, it must produce a Directed Test Guidance table that testbench-dev can directly consume. This closes the Coverage-Driven Test Generation loop with structured, actionable feedback — not just gap descriptions.
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.
- 20d ago First seen · 225 lines · 25 tokens per session scan A 2e8573408979
rtl-p5s-coverage-policy is a skill published in the GitHub repository babyworm/rtl-agent-team (61 stars, last pushed 21d ago), licensed MIT. It adds 25 tokens to every session and 2,719 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, attach a workspace, defer capability…
verification-strategy
Thorough verification of completed work before declaring done.
image-compare
Compare two image files on disk and report what changed, region by region. Trigger on "what changed between these two images", "diff these PNGs", "did this render drift", "compare screenshots/exports/renders".
test-sqrl
Use when adding or updating tests for a DataSQRL pipeline. Use after implementing features to verify correctness.
qa-review
QA review for code changes — test coverage analysis, edge case identification, test plan generation, regression detection, test health tracking over time.
lastlight-evals-loop
Drive a Last Light EVAL toward a target score with a disciplined, anti-gaming improvement loop — run → mine failures → propose candidate fix(es) → re-measure → keep the best or revert → repeat. Use when the user wants to "improve / raise the pr-review F1", "make the reviewer better against the eval", "close the loop…