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 richfrem/agent-plugins-skills --skill os-skill-improvementgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/os-skill-improvement)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-skill-improvement"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-skill-improvement/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/richfrem/agent-plugins-skills/os-skill-improvement"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-skill-improvement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00133 | $0.01229 |
| Opus 5 | $0.00067 | $0.00615 |
| Sonnet 5 | $0.00027 | $0.00246 |
| Haiku 4.5 | $0.00013 | $0.00123 |
Grade A, and why
os-skill-improvement 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 yesterday.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Continuous Improvement: RED-GREEN-REFACTOR
Adapts the RED-GREEN-REFACTOR cycle from software testing to skill authoring. The key insight: a skill is a testable contract. The failure to follow the contract is observable. Always observe the failure BEFORE writing the fix.
Integrated with:
os-eval-runner-- runseval_runner.pyas the GREEN verification stepos-improvement-loop-- uses this methodology to gate every proposed skill patchevals/evals.json+results.tsv-- autoresearch eval format for longitudinal tracking
The TDD Mapping
| Software TDD | Skill Authoring Equivalent |
|---|---|
| Test case | Pressure scenario: a user prompt that should trigger the skill |
| RED phase | Run a baseline WITHOUT the skill. Observe: does the agent violate the intended protocol? |
| GREEN phase | Write the skill. Run os-eval-runner. KEEP only if score >= baseline. |
| REFACTOR phase | Identify loopholes from eval failures. Patch frontmatter or examples. Re-eval. |
Iron Law: Run a RED Scenario BEFORE Writing
Never write a new skill without first observing a failure.
The RED scenario is the evidence that the skill is needed. Without it you cannot know the
specific failure being fixed, cannot do a before/after comparison, and examples become
generic rather than addressing real failure modes. Full steps for running a RED scenario are
in references/detailed-reference.md.
Required before any mutation
- Skill State Snapshot — run
eval_runner.py --skill <experiment-dir> --snapshotto see current score, iteration history, and whether the dominant problem is PRECISION (too many false positives — don't add more keywords) or RECALL (don't add adversarial examples without also adding trigger phrases). Full detail inreferences/detailed-reference.md. - Hypothesis Block — output failure mode, root cause, change, expected effect, and named
regression risk before editing any file. Format and worked example in
references/detailed-reference.md. Vague hypotheses ("description too vague") are not acceptable — they produce random mutations and early plateau.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 662 B
- evals/results.tsv 155 B
- references/acceptance-criteria.md 42 B
- references/detailed-reference.md 62 B
- references/fallback-tree.md 57 B
- references/memory/improvement-ledger-spec.md 56 B
- references/operations/skill_optimization_guide.md 61 B
- references/testing/test-registry-protocol.md 56 B
- scripts/eval_runner.py 31 B runs code
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.
- yesterday Changed · -212 lines c96c6832371e
- 9d ago First seen · 311 lines · 133 tokens per session scan A ba4f7bb18459
os-skill-improvement is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 133 tokens to every session and 1,229 once invoked, about $0.0007 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
test-verification
Requires behavioral, failure-path, and durable-seam evidence for tests and review. Use when writing tests, reviewing test coverage, assessing behavioral test quality, or accepting high-risk behavior on test evidence.
test-writing
Write comprehensive tests for code including unit tests, integration tests, and end-to-end tests. Use this to ensure code quality, catch bugs, and validate functionality.
tdd-xfail
Use when fixing a bug through strict xfail reproduction and needing proof that the test fails for the intended reason.
concept-implementation
An implementation skill for turning a confirmed concept model into a modular monolith, a single deployable application split into independent modules.
a11y-testing
Use this skill when the user asks about accessibility testing, axe-core, jest-axe, "@testing-library", "@axe-core/playwright", "Playwright accessibility testing", "WAVE", "Lighthouse accessibility", "automated a11y tests", "accessibility CI/CD", "eslint-plugin-jsx-a11y", "a11y linting", "axe DevTools", setting up…
fortify
Testing infrastructure, coverage, and verified test quality for any project. Detects stack, installs testing ecosystem, audits untested critical paths, writes thorough tests weighted toward error paths, runs them, verifies via mutation testing. Use when user says '/fortify', 'add tests', 'set up testing', 'I need…