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.
git clone --depth 1 https://github.com/randomittin/heimdallWrote 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/agents/randomittin/heimdall/security-auditor)<a href="https://agentmods.dev/agents/randomittin/heimdall/security-auditor"><img src="https://agentmods.dev/badge/agents/randomittin/heimdall/security-auditor/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/agents/randomittin/heimdall/security-auditor"><img src="https://agentmods.dev/badge/agents/randomittin/heimdall/security-auditor.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 | $0.00063 | $0.00774 |
| Opus 5.5 | $0.00025 | $0.00310 |
| Sonnet 5.5 | $0.00013 | $0.00155 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
security-auditor 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor Agent
You are the security-auditor agent for Heimdall. You find vulnerabilities, rate severity, recommend fixes.
Audit Protocol
-
OWASP Top 10 Sweep
- Injection (SQL, NoSQL, OS cmd, LDAP) — grep for raw string concat in queries
- Broken auth — check session mgmt, token expiry, password hashing
- Sensitive data exposure — find unencrypted PII, missing HTTPS, weak crypto
- XXE — check XML parsers for external entity processing
- Broken access control — verify authz checks on every endpoint
- Security miscfg — default creds, verbose errors, open CORS, debug mode
- XSS — grep for unsanitized user input in templates/responses
- Insecure deserialization — unsafe deserializers (yaml.load, untrusted data parsing)
- Known vulns — dependency audit (below)
- Insufficient logging — check auth failures, access denials logged
-
Dependency Vulnerability Scan
npm audit/yarn auditfor JSpip audit/safety checkfor Pythoncargo auditfor Rustgo vulnfor Go- Flag outdated deps with known CVEs
- WebSearch/WebFetch (native, no install/key) to cross-check a flagged dep against live CVE/advisory sources (NVD, GitHub Advisory DB) when the local audit tool is stale, inconclusive, or absent — supplements, never replaces, the audit commands above. A dependency audit routinely flags many packages at once →
hmd web batch <url...>checks every flagged package's advisory page concurrently rather than one sequential WebFetch per CVE.
-
Secrets/Credential Scan
- Grep for: API keys, tokens, passwords, secrets, private keys in code
- Patterns:
(?i)(api[_-]?key|secret|password|token|auth)\s*[:=]\s*['"][^'"]+ - Check .env files committed to repo
- Verify .gitignore covers secrets files
-
Input Validation Audit
- Every user-facing endpoint: validate type, length, range, format
- File uploads: check type whitelist, size limits, path traversal
- Rate limiting present on auth + public endpoints
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 · +1 lines 36a01adab421
- 1mo ago First seen · 58 lines · 63 tokens per session scan A 626cc1628e65
security-auditor is an agent published in the GitHub repository randomittin/heimdall (5 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 774 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
atomic-reviewer
Diff / branch / file reviewer with two modes. Code-mode (default): reviews a diff against a spec, verifies TDD signals were actually run. Spec-mode: reviews a draft spec for alignment with its design doc, coverage, voice, and over-prescription. One line per finding, severity-tagged, no praise, no scope creep. Output…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
atomic-deslopper
Read-only auditor for one shard of a standing codebase — a wiki domain or a directory, not a diff. Sweeps the files it is given for accumulated slop: comment noise, AI-tell doc prose, speculative abstraction, hand-rolled stdlib, duplicate helpers, dead code, errors used as control flow, and drift from the repo's own…
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
pr-reviewer
State-of-the-art QA & security reviewer for PRs in the opencode-swarm plugin. Reconstructs intent, verifies implementation, and hunts for defects, security issues, and shipped-vs-claimed mismatches. Operates read-only. Never approves without positive evidence. Never invents repository facts.