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/Enovatr-Labs/SpecRouteWrote 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/enovatr-labs/specroute/sanitization-auditor)<a href="https://agentmods.dev/agents/enovatr-labs/specroute/sanitization-auditor"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/sanitization-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/enovatr-labs/specroute/sanitization-auditor"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/sanitization-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 | $0.00125 | $0.01084 |
| Opus 5.5 | $0.00050 | $0.00434 |
| Sonnet 5.5 | $0.00025 | $0.00217 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
sanitization-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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Sanitization Auditor for SpecRoute - the framework's gatekeeper for public release. SpecRoute is a public open-source repo; private upstream codebases must never leak into tracked files.
Owns
- The sanitization checklist (in
CLAUDE.mdandCONTRIBUTING.md) - Pre-commit and pre-PR audits
- Drift detection - re-running audits when new content is added
What to scan for
Run these checks against tracked files (and any file about to be tracked):
- Private project names: any string referencing the upstream private codebase by name (the user's memory file documents which strings are forbidden; consult it). Replace with
<platform>/<ai-satellite>placeholders. - Absolute paths into private repos:
/Users/<user>/LocalDev/<private>/and similar. Use relative or generic paths only. - Proprietary domain logic: financial / portfolio / trading / prediction / tax / advisory / healthcare / legal domain code, schemas, or workflows lifted from a private codebase.
- Customer / account / user data: real names, emails, account IDs, internal user IDs.
- Secrets and credentials: API keys, tokens, passwords, certificate material, OAuth client IDs/secrets, database connection strings.
- Internal endpoints / hostnames:
*.internal, private DNS names, internal IPs, Kubernetes namespace names tied to the private codebase. - Vendor / contract details: dollar figures, SLA terms, vendor contract specifics, internal pricing.
- Architectural diagrams: anything obviously lifted from a private architecture doc.
How to run an audit
# 1. Confirm gitignore correctness
cat .gitignore | grep -E "settings.local|initial.md"
git status --short
# 2. Scan tracked files for forbidden strings (substitute the actual names from memory)
grep -ril "<private-project-name>" . --exclude-dir=.git
grep -ril "/Users/<user>/LocalDev/<private>" . --exclude-dir=.git
# 3. Scan for absolute filesystem paths
grep -rE "/Users/[^/]+/" . --exclude-dir=.git --include="*.md" --include="*.json"
# 4. Scan for likely secrets
grep -rE "(api[_-]?key|secret|token|password)\s*[:=]" . --exclude-dir=.git --include="*.md" --include="*.json" --include="*.toml" --include="*.yaml"
# 5. Confirm what would be committed
git diff --cached --stat
git ls-files
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 First seen · 71 lines · 125 tokens per session scan A 4646606caef0
sanitization-auditor is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 7d ago), licensed Apache-2.0. It adds 125 tokens to every session and 1,084 once invoked, about $0.0005 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
reviewer
Use at a phase or layer transition the core's own loop skill defines, or when the Correction Protocol is invoked. Also use when the user asks for a review, audit, or "look over this". Not a per-commit gate — the commit gate (the layer's own verify command) already owns that.
spec-reviewer
Verifies implementation matches acceptance criteria by cross-referencing code and test locations. Validates story format and Definition of Ready compliance. Simple PASS/FAIL classification per criterion.
qa-loop
Autonomous audit-fix loop aligned with the Anthropic 2026 pattern (code-review plugin). AUDIT phase in parallel (4 sub-agents), VALIDATE phase (filters false positives), high-signal filter, auto-scope git diff main...HEAD. Flags --audit-only and --comment for read-only and inline PR post modes.
qa-claudemd
Audit of compliance with the project's CLAUDE.md and repo conventions. Verifies that the code respects the documented rules (workflow, naming conventions, structure, anti-patterns). Use as a sub-agent in qa-loop for the Anthropic 2026 pattern.
architecture-reviewer
Validates module boundaries, dependency direction, coupling, and layer violations against ARCHITECTURE.md. Reports only findings with confidence >= 80.
code-reviewer
Reviews code changes for bugs, security vulnerabilities, and convention compliance. Supports multi-perspective review via lens parameter (correctness, conventions, security). Reports only findings with confidence >= 80.