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-persona-self-idgit 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-persona-self-id)<a href="https://agentmods.dev/skills/cosai-oasis/secure-ai-tooling/explore-persona-self-id"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/explore-persona-self-id/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-persona-self-id"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/explore-persona-self-id.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 | $0.00150 | $0.00766 |
| Opus 5.5 | $0.00060 | $0.00306 |
| Sonnet 5.5 | $0.00030 | $0.00153 |
| Haiku 4.5 | $0.00015 | $0.00077 |
Grade A, and why
explore-persona-self-id 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 15d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore: Which Persona Am I?
Guide a reader to their CoSAI Risk Map persona(s) using the framework's own identificationQuestions, then orient them to what that role must care about. Read-only.
Audience and voice
Security-literate, new to CoSAI-RM. Explain what a persona/risk/control is; link entity ids. This is a guide, not an assessment of their security posture.
How to answer
- Gather signal. If the reader described their AI activities, use that. If they gave little, or the activity is ambiguous between adjacent roles, ask the
identificationQuestions— readrisk-map/yaml/personas.yamland pose the most-distinguishing questions (a guided walkthrough). (Explain: a persona is a role across the AI lifecycle; its identificationQuestions are activity-based yes/no self-ID questions.) - Identify the persona(s). Match the answers to the persona whose questions they satisfy — and cite which questions matched. A reader may map to more than one (e.g. primarily Application Developer, partially Agentic Platform and Framework Providers); explain the scoping rather than forcing a single answer.
- Explain the role. The persona's
description+responsibilities— what this role is accountable for. - Orient to exposure and duties. For the identified persona, surface both sides of the persona model:
- Risks that impact you — risks whose
personaslist includes your persona (you bear the consequences). - Controls you implement — controls whose
personaslist includes your persona (you are responsible for deploying them). (Explain: risks list impacted parties; controls list implementers — so your persona appears in both, meaning different things.)
- Risks that impact you — risks whose
- Link ids and point to
explore-risks-by-activity(deeper exposure) orexplain-entity(any specific entry) for drill-down.
Output (adaptive)
- Enough signal → identify the persona(s) + a concise briefing: your role · your risks · your controls.
- Not enough signal → guided: ask 2–4 distinguishing
identificationQuestions, then identify. - Multiple personas → name each and explain the boundary between them.
- Always link 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.
- 15d ago First seen · 40 lines · 150 tokens per session scan A 1d922fb46b96
explore-persona-self-id is a skill published in the GitHub repository cosai-oasis/secure-ai-tooling (100 stars, last pushed today), licensed Apache-2.0. It adds 150 tokens to every session and 766 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…