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 smk-labs/claude-plugins --skill self-assessgit clone --depth 1 https://github.com/smk-labs/claude-pluginsWrote 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/smk-labs/claude-plugins/self-assess)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/self-assess"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/self-assess/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/smk-labs/claude-plugins/self-assess"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/self-assess.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 | $0.00059 | $0.01627 |
| Opus 5.5 | $0.00024 | $0.00651 |
| Sonnet 5.5 | $0.00012 | $0.00325 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
self-assess 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
self-assess: find the real level, not the claimed one
The output is one file, PROFILE.md, and it aims everything that comes after it. If it is wrong, the whole course is wrong, so accuracy here is worth more than speed.
Read reference/quiz-craft.md before writing a single question. It is the difference between a quiz that measures and a quiz that flatters.
Ground rules
You never teach during a quiz. No hints, no feedback between batches, no encouragement that leaks an answer. All explanation waits until the end.
You never delegate the interaction. Every question is asked from this session. Subagents may help you survey the domain beforehand; they never talk to the learner. Run this on the strongest model available, because the real work is reading a vague or partial answer and correctly deciding whether it shows knowledge, intuition, or a guess.
"I do not know" is a good answer. It is the cleanest signal in the whole exercise. Never discourage it, and always leave the free-text option open.
Step 0: which kind of assessment is this
Three situations, and they need different questions.
- New subject, no course yet. The default. Cover the whole domain and write a fresh
PROFILE.md. - An existing course, before or between books. Read
PROFILE.md,TOC.mdandprogress/log.mdfirst. Aim the questions at what the course has already taught and at the gaps the old profile recorded. The point is to measure movement, so write the result as a new dated section inPROFILE.mdnext to the original, never over it. A profile that gets overwritten destroys the only before-and-after this system has. - One specific book or chapter that was already taught. Draw the questions from that book's own lesson list and quiz topics in
books/, rephrased so recall does not substitute for understanding. Never reuse a question they have already answered: ask the same mechanism from a different angle. Report per chapter so they can see exactly what did not stick, and note it inprogress/log.md.
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 Changed · +3 lines · -99 tokens per session dea5be3efa49
- 1mo ago First seen · 99 lines · 158 tokens per session scan A 3712401fa0d2
self-assess is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 28d ago), licensed MIT. It adds 59 tokens to every session and 1,627 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
meta-learn
Captures a completed skill session in depth: three extraction questions (what surprised you, what was wrong, what was missing) become falsifiable pattern statements, logged to /context/skill-sessions.md for meta-synthesis. Trigger on: "capture what we learned", "log this session", "save the learnings", "what did we…
pmm-resume
Reviews and tailors a PMM resume (IC to VP, including AI PMM roles): dissects the job description, ranks bullets by impact fit and rebuilds the complete resume in one pass. Trigger on: resume + JD paste, "tailor this", "which bullets for this role", "rebuild for [company]", "review my PMM resume", "reframe for…
product-marketing-context
Builds and maintains the shared GTM brain (product context, ICP, positioning, voice, market context, proof points, plus optional strategy and execution sections and the deal-reality fields) that every other skill reads before producing output. Works standalone from your own answers, and gets stronger when you connect…
competitor-deep-dive
Builds a long-form, fully sourced deep-dive on one competitor for a named decision (strategy call, RFP, pricing change, roadmap bet), with dated reviews, deal evidence, a head-to-head per offering and where they win. Triggers: "deep-dive on [competitor]", "full competitor write-up", "what do users really say about…
workflow-orchestrator
Chains positioning, competitive, GTM strategy, campaign briefs, stakeholder maps and retros into one coherent PMM program with a master document and brain updates. Trigger on: "run full GTM workflow", "run a full launch", "launch [product] end to end", "positioning refresh", "quarterly PMM cycle", "competitive…
positioning-messaging
Builds or audits positioning statements, messaging hierarchies, homepage copy and persona cards using April Dunford's Obviously Awesome framework, in five modes (build, audit, fletch, sales-enablement, homepage). Refuses to generate without a named primary persona and 3+ alternatives including status quo, and blocks…