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 ArtemioPadilla/agent-triforce --skill security-auditgit clone --depth 1 https://github.com/ArtemioPadilla/agent-triforceWrote 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/artemiopadilla/agent-triforce/security-audit)<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/security-audit"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/security-audit/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/artemiopadilla/agent-triforce/security-audit"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/security-audit.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 | $0.00041 | $0.00857 |
| Opus 5 | $0.00020 | $0.00428 |
| Sonnet 5 | $0.00008 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
security-audit 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 11d 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.
What it actually says
Perform a security audit on: $ARGUMENTS
If no specific scope is provided, audit the entire src/ directory.
Follow these steps:
SIGN IN:
- Run the SIGN IN checklist from your agent file
- Note areas of concern based on the scope and past findings
AUDIT:
- OWASP Top 10 systematic check:
- A01: Broken Access Control — check auth/authz on all endpoints
- A02: Cryptographic Failures — check encryption, key management, hashing
- A03: Injection — SQL, NoSQL, OS command, LDAP injection vectors
- A04: Insecure Design — business logic flaws, missing rate limits
- A05: Security Misconfiguration — default configs, verbose errors, CORS
- A06: Vulnerable Components —
npm audit/pip audit - A07: Auth Failures — weak passwords, missing MFA, session management
- A08: Data Integrity — deserialization, unsigned updates
- A09: Logging Failures — sensitive data in logs, missing audit trail
- A10: SSRF — server-side request forgery vectors
- Secrets scan: grep for API keys, tokens, passwords, connection strings
- Dependency audit: check all deps for known CVEs
- Smart contracts (if Solidity): reentrancy, integer overflow, access control, front-running
- Architecture review: Check dependency direction (business logic must not depend on frameworks), verify layer separation (no auth bypass through adapter shortcuts, no direct DB access from use cases)
- Test strategy review: Verify security-critical paths have tests, authentication/authorization flows are integration-tested, input validation has unit tests
License Compliance Scan
Scan all project dependencies for license compatibility with the project license (MIT):
- Detect dependency manifest:
requirements.txt,pyproject.toml(Python) orpackage.json(Node) - Check each dependency's license using
pip-licenses --format=markdown(Python) ornpx license-checker --json(Node). If tools unavailable, inspect manifests manually - Classify by compatibility:
- Pass (permissive): MIT, BSD-2-Clause, BSD-3-Clause, Apache-2.0, ISC, Unlicense, CC0-1.0, 0BSD
- Warning (weak copyleft): LGPL-2.1, LGPL-3.0, MPL-2.0, EPL-1.0, EPL-2.0 -- flag with explanation of linking implications
- Critical (strong copyleft): GPL-2.0, GPL-3.0, AGPL-3.0 -- incompatible with MIT distribution
- Critical (no license): Dependency has no detectable license -- cannot legally redistribute
- Output: License compatibility table in the security audit report with columns: Dependency, Version, License, Compatibility (Pass/Warning/Critical)
References: Skaife (2021), EPAM SolutionsHub (2023), Leroux (2025)
If any Critical finding: invoke the NON-NORMAL: Critical Vulnerability Response checklist from your agent file.
⏸️ TIME OUT — Run Verification Checklists (DO-CONFIRM): 7. Run through the Security Verification checklist from your agent file 8. Run through the Quality Verification checklist from your agent file 9. Issue verdict based on findings
SIGN OUT:
10. Write report to docs/reviews/security-audit-{date}.md
11. Write the Findings Handoff-to-Forja using the communication checklist
12. Run the SIGN OUT checklist from your agent file
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.
- 11d ago First seen · 65 lines · 41 tokens per session scan A a3fe5116f132
security-audit is a skill published in the GitHub repository ArtemioPadilla/agent-triforce (3 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 857 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
fellowship
Multi-task orchestrator. Coordinates agent teammates (led by Gandalf) running /quest (code) or /scout (research) workflows. Use when you have multiple independent tasks to run in parallel.
quest
Use for multi-file or multi-step changes that need research and a plan — not single-file fixes under 50 lines that follow an existing pattern (see Escape Hatch below). Runs the Research → Plan → Implement → Review lifecycle with a hard gate leaving each of the first three phases and context compaction between them.
retro
Invoke after a fellowship disbands, or when the user explicitly asks for a retrospective. Collects gate history, palantir alerts, and quest metrics to surface patterns and interactively recommend configuration improvements.
council
Invoke when the user runs /council or from /scout. Quest inlines this orientation as its Research step 2 and does not call it. Loads focused, task-relevant context by reading CLAUDE.md, scanning for related files, and producing a structured Session Context block.
lembas
Use between workflow phases or when context feels bloated. Writes a structured checkpoint capturing task, findings, files, state, and next steps, then continues from that summary instead of the full history. Invoke standalone or automatically between quest phases.
missive
Invoke only when spawning a quest from a GitHub issue reference. Fetches GitHub issue context for quest spawning. Parses issue references, retrieves structured data via gh, and produces branch suggestions and PR keywords. Used standalone or as input to quest orchestration.