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 refactor-classification-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/refactor-classification-policy)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/refactor-classification-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/refactor-classification-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/refactor-classification-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/refactor-classification-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 33 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00021 | $0.00406 |
| Opus 5.5 | $0.00008 | $0.00162 |
| Sonnet 5.5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
refactor-classification-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 1mo 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
Refactor Policy
Refactor Classes
SAFE: behavior-preserving cleanup with no interface/timing contract impactRESTRICTED: likely behavior-preserving but affects structure or test assumptionsPROHIBITED: behavior/spec contract may change
SAFE (auto-apply allowed)
- Naming/format consistency fixes
- Dead code removal
- Local duplication cleanup with equivalent logic
- Comment/documentation synchronization
RESTRICTED (approval or explicit orchestrator permit)
- Significant module decomposition/merge
- Testbench structure reshaping affecting check points
- Constraint file reorganization without semantic change proof
PROHIBITED (manual approval required)
- FSM semantic changes
- Pipeline latency/stage changes
- CDC strategy changes
- Interface contract changes
- Reset behavior semantics changes
Pass/Fail Gate
FAIL: any prohibited change applied without approvalFAIL: equivalence confidence not demonstrated for SAFE/RESTRICTED changesPASS: only SAFE changes applied and mandatory recheck passed
Escalation
- Any ambiguity about behavior equivalence: escalate as
RESTRICTED - Any proposal touching interface/timing contract: escalate before edit
- Repeated recheck fail after 2 attempts: stop and hand off with root-cause note
Output Format
Use the following refactor execution report:
# Refactor Execution Report
- Scope: module|block|top
- Verdict: PASS | FAIL
## Planned Changes
| ID | Class | Target | Rationale | Approval Required |
|---|---|---|---|---|
## Applied Changes
| ID | Files | Summary | Risk |
|---|---|---|---|
## Blocked/Deferred
- [approval-required or risky items]
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.
- 1mo ago First seen · 61 lines · 21 tokens per session scan A 138e20814f1c
refactor-classification-policy is a skill published in the GitHub repository babyworm/rtl-agent-team (61 stars, last pushed 21d ago), licensed MIT. It adds 21 tokens to every session and 406 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 2026-09-03.
Other skills, from other repositories
aster-review-ci
Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.
qa-review
QA review for code changes — test coverage analysis, edge case identification, test plan generation, regression detection, test health tracking over time.
kicad-pcb-review
Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.
module-no-new-exports-all
Populate no-new-exports entries in module descriptors so their module surface area cannot be increased.
refactor-safely
Renaming, moving, and restructuring code without breaking behavior. Use when the task is a rename, a file move, an extract, or any restructuring the user expects to be behavior-neutral.
apex-review
Reviews a technical proposal from the perspective of organizational decision-makers (CTO, technical lead, QA lead, conference reviewers, etc.) and generates an HTML presentation deck. Outputs approval gate results per persona and connects to sim-conductor for improvement suggestions.