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 explore-controls-by-classicalgit 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/explore-controls-by-classical)<a href="https://agentmods.dev/skills/cosai-oasis/secure-ai-tooling/explore-controls-by-classical"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/explore-controls-by-classical/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/explore-controls-by-classical"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/explore-controls-by-classical.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 | $0.00145 | $0.00768 |
| Opus 5.5 | $0.00058 | $0.00307 |
| Sonnet 5.5 | $0.00029 | $0.00154 |
| Haiku 4.5 | $0.00015 | $0.00077 |
Grade A, and why
explore-controls-by-classical 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 13d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore Controls by Classical Concept
Help someone who knows classical security find its analogues among the CoSAI controls, and see how the framework extends the concept to AI/agentic systems. Read-only.
This is the consumer, read-only sibling of the classical-lexicon skill (which grounds terminology at authoring time). Reuse its lexicon for the grounding — do not re-derive or duplicate it.
Audience and voice
Classical-security-literate, new to CoSAI-RM. Explain framework terms (control, the risks a control addresses); link every control id; make the classical→AI bridge explicit.
How to answer
- Ground the classical concept. Consult the
classical-lexiconskill for the canonical term of art and its meaning/aliases (e.g. "PEP" = Policy Enforcement Point, NIST SP 800-207 / 800-162). Confirm you're mapping the right concept. - Find the controls that embody it. Search
risk-map/yaml/controls.yaml— the corpus already grounds many controls classically (e.g. "least-privilege principle", "reference monitor", "attestation", "provenance", "confused deputy"). Grep the canonical term and its synonyms across control titles,descriptionandguidance. - Explain the bridge. For each matching control: id + title, how it embodies or extends the classical concept, and the AI-specific amplifier (what's different/harder in AI/agentic systems). Distinguish "directly embodies" from "related/adjacent".
- Attach exposure. Note the risks each surfaced control addresses (its
risksfield) so the reader sees what it's for. - No clean match? Say so plainly and point to the nearest controls; note it may be a coverage gap. Surface it — do not author.
Output (adaptive)
- "what controls map to X" → table:
Control (id — title)| how it embodies X | risks it addresses. - "how does X show up in the framework" → a narrative classical→AI bridge.
- Unknown/ambiguous concept → confirm it via
classical-lexicon, then answer. - Always link control ids; note this reflects the current corpus.
What ships with it
1 file 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.
- 13d ago Changed 231d7860e7d7
- 15d ago First seen · 41 lines · 145 tokens per session scan A b0904784f127
explore-controls-by-classical is a skill published in the GitHub repository cosai-oasis/secure-ai-tooling (100 stars, last pushed today), licensed Apache-2.0. It adds 145 tokens to every session and 768 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 2026-10-01.
Other skills, from other repositories
svc-mobile-android
Android APK static analysis — OWASP Mobile Top 10, Retrofit API audit, transport security, smali reading, component export, auth flow analysis. Use when target is an APK/Android app. Triggers - APK, Android, mobile app, decompiled, smali, jadx, apktool.
svc-pivoting
Turn a foothold into a RELIABLE pivot (SOCKS tunnel + persistent shell) so internal volume never rides a fragile stateless RCE. Use the moment you have code-exec on a dual-homed/edge host and need to reach an internal segment. Triggers - dual-homed host, "not reachable from my box", internal CIDR behind a foothold…
web-auth-bypass-idor
Broken access control - IDOR, privilege escalation, JWT abuse, mass assignment, forced browsing - for web apps and APIs. Use on any multi-user or role-based app with object IDs, tokens, or admin functionality. Triggers - /api/users/ , /orders/ , ?account=/uid=/doc=, JWT (eyJ...), role/isAdmin field, admin panel, "403…
web-deserialization
Insecure deserialization to RCE for web apps. Use when the app deserializes attacker-controlled data - cookies/tokens/hidden fields/params that are serialized blobs, VIEWSTATE, Java/PHP/.NET/Python/Node apps. Triggers - base64 starting rO0AB or hex AC ED 00 05 (Java), PHP serialize O-prefix, VIEWSTATE, python pickle…
web-lfi-traversal
Path traversal / Local File Inclusion detection→file-read→RCE for web apps. Use when a param names a file/path/page/template/lang/download, or a response embeds file contents. Triggers - file=/page=/path=/template=/lang=/download=/include= param, ../, %2e%2e, "no such file", directory listing, download endpoint.
web-sqli
SQL injection detection→exploitation→proof for web apps and APIs. Use when a parameter reaches a DB query, when input triggers a SQL error / boolean or time differential, or during VULN-ASSESSMENT/EXPLOITATION on a web target. Triggers - sql syntax error, ORA-/MySQL/psql/SQLite error string, ' or 1=1, order by…