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 cosai-oasis/secure-ai-tooling --skill altitude-checkgit clone --depth 1 https://github.com/cosai-oasis/secure-ai-toolingWrote 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/cosai-oasis/secure-ai-tooling/altitude-check)<a href="https://agentmods.dev/skills/cosai-oasis/secure-ai-tooling/altitude-check"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/altitude-check/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/cosai-oasis/secure-ai-tooling/altitude-check"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/altitude-check.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 | $0.00146 | $0.01285 |
| Opus 5.5 | $0.00058 | $0.00514 |
| Sonnet 5.5 | $0.00029 | $0.00257 |
| Haiku 4.5 | $0.00015 | $0.00128 |
Grade A, and why
altitude-check 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Altitude Check
Altitude is the granularity an entry is pitched at. Too low and it becomes implementation detail or an instance that sprawls into siblings; too high and it dissolves the gap it was meant to name. Most authoring defects are altitude defects, so check altitude before wording.
Run the tests for the entry type. The control, risk, and component tests are all active; run the set matching the entry type.
Control altitude tests
Apply each; report pass or adjust-with-fix.
- T1 — Objective, not implementation. The control states a capability or objective ("ensure delegation chains are auditable"), not a mechanism ("emit signed delegation spans with correlation IDs to a collector"). The objective survives implementation churn. Fix: move the mechanism into the implementation section of
guidance(DG5 inrisk-map/docs/design/control-description-and-guidance.md) and restate the objective indescription. - T2 — Not a restated risk. A control is the defense framed as a positive capability, not the threat with "prevent" attached. If it reads like the risk inverted, rewrite it as the capability the implementer gains.
- T3 — Posture, not mandate. A control describes a defensive capability an implementer adopts against their risk appetite; it is not a compliance order. Watch for "must always," universal imperatives, and audit-language.
- T4 — Solved problem. A known technique achieves the objective. If none does, this is a research gap or a risk to document — not a control. Fix: flag it for the maintainer rather than drafting an aspirational control.
- T5 — Generalized and grounded. The control names a role/locus, not a product or protocol, and uses established terminology (defer terminology to the classical-lexicon skill). Fix: generalize
descriptionto the role; keep the product inguidance(implementation or applicability), never indescription. - T6 — Novelty vs absorb. Read
risk-map/yaml/controls.yaml. Does an existing control already cover this objective? If so, recommend augmenting that control rather than adding a near-duplicate. If genuinely distinct, state in one sentence what distinguishes it from the nearest existing control. Placement: that sentence goes in the boundary section ofguidance(last section,{{control…}}sentinel; DG4, DG10), not indescription.
What ships with it
2 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.
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 75553de62ab8
- 2mo ago First seen · 45 lines · 146 tokens per session scan A 32e3217bcc3a
altitude-check is a skill published in the GitHub repository cosai-oasis/secure-ai-tooling (102 stars, last pushed 3d ago), licensed Apache-2.0. It adds 146 tokens to every session and 1,285 once invoked, about $0.0006 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
playbook-webapp
Web application pentest methodology + ROUTER to the per-vuln-class web skills. Load at the START of systematic web testing to get the phase flow (recon → map → test-by-OWASP-class → prove → report) and pick which web- skill to load for each surface. Use on any web app / HTTP API engagement.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
emerging-techniques-model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.