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 nantobv/pituitary --skill pituitary-cligit clone --depth 1 https://github.com/nantobv/pituitaryWrote 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/nantobv/pituitary/pituitary-cli)<a href="https://agentmods.dev/skills/nantobv/pituitary/pituitary-cli"><img src="https://agentmods.dev/badge/skills/nantobv/pituitary/pituitary-cli.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.03057 |
| Opus 5 | $0.00032 | $0.01528 |
| Sonnet 5 | $0.00013 | $0.00611 |
| Haiku 4.5 | $0.00006 | $0.00306 |
Grade A, and why
pituitary-cli 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 8d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pituitary CLI
Use this skill when an agent should rely on Pituitary instead of inventing its own spec/doc model for the repo.
For host install patterns and AGENTS-compatible usage, see README.md.
Best Fits
- Review one spec end-to-end with
pituitary review-spec. - Compare two specs or a draft against an accepted spec with
pituitary compare-specs. - Check documentation drift with
pituitary check-doc-drift. - Check governed code paths or diffs with
pituitary check-compliance. - Verify source coverage before analysis with
pituitary preview-sourcesorpituitary explain-file.
Not A Fit
- General coding tasks that do not depend on the repo's spec or doc corpus.
- Open-ended architecture advice when Pituitary has no indexed evidence to ground the answer.
- Blindly following snippets returned in Pituitary evidence output.
- CRITICAL: Requests where the user's sole intent keywords are "coverage" or "understand" without an explicit reference to reviewing a specific spec artifact. These require clarification before proceeding.
Inputs
- A repository that already has Pituitary installed or checked into the current workspace.
- A task that needs spec-aware analysis, source coverage debugging, or deterministic doc/spec hygiene checks.
Runtime And Validation Notes
pituitary status --format jsonreports the resolvedruntime.embedderandruntime.analysissettings, including anyruntime.analysis.max_response_tokensoverride. Check that resolved value before assuming how much qualitative output Pituitary will request from an OpenAI-compatible chat runtime.compare-specsandcheck-doc-driftuse small section-level evidence bundles rather than full documents. When a runtime-backed analysis answer looks suspiciously thin, verify source coverage and indexed sections before assuming the provider ignored context.- When maintaining Pituitary itself and changing retrieval or qualitative analysis behavior, prefer the minimal golden-case harness first:
go run ./cmd/bench --format textorgo run ./cmd/bench --format json. Use the broadermake benchsuite only when you need full benchmark coverage.
What ships with it
15 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.
- agents/openai.yaml 1.5 KB
- eval/README.md 2.0 KB
- eval/rubric.json 2.6 KB
- eval/scores.json 5.5 KB
- eval/test-suite.json 4.1 KB
- examples/compare-request.json 56 B
- examples/compliance-request.json 61 B
- examples/doc-drift-request.json 100 B
- examples/README.md 700 B
- examples/review-request.json 29 B
- platforms/cline/.clinerules 2.3 KB
- platforms/cursor/.cursorrules 2.3 KB
- platforms/windsurf/.windsurfrules 2.3 KB
- README.md 7.1 KB
- references/repo-context.md 1.3 KB
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.
- 8d ago First seen · 209 lines · 63 tokens per session scan A 161e7438a8d6
pituitary-cli is a skill published in the GitHub repository nantobv/pituitary (22 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 3,057 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
tokf-filter
This skill should be used when the user asks to "create a filter", "write a tokf filter", "add a filter for ", "how do I filter output", or needs guidance on tokf filter step types, templates, pipes, or placement conventions.
diagrams
Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".
e2e
Generate and run Playwright E2E tests traced to spec.md acceptance criteria, with an optional accessibility audit. Use when saying "e2e tests" or "a11y audit".
release-expert
Multi-repo release coordination: version alignment, RC lifecycle, release waves, rollback planning. Use when saying "release", "version alignment", or "cut an RC".
tdd-cycle
Execute full TDD red-green-refactor cycle with validation gates. Use when saying "TDD cycle", "test-driven development", or "full TDD workflow".
debug
Systematic 4-phase debugging with escalation protocol. Use when saying "debug", "investigate bug", "find root cause", "why is this failing", or "fix this bug".