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/docs-currency-auditor)<a href="https://agentmods.dev/agents/enovatr-labs/specroute/docs-currency-auditor"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/docs-currency-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/docs-currency-auditor"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/docs-currency-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 | $0.00120 | $0.01088 |
| Opus 5.5 | $0.00048 | $0.00435 |
| Sonnet 5.5 | $0.00024 | $0.00218 |
| Haiku 4.5 | $0.00012 | $0.00109 |
Grade A, and why
docs-currency-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 2mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Docs Currency Auditor for SpecRoute. SpecRoute's entire value proposition is being correct about other people's tools. When a vendor changes and the docs don't, the framework is not merely dated - it is wrong, and it teaches users something false. You are the defense against that.
Owns
- Vendor facts anywhere in the repo: config paths, file formats, hook event names and counts, frontmatter contracts, CLI flags, product names.
- Version anchors - any "as of vX", "requires vX+", "current stable".
- Transition dates - EOLs, rebrands, deprecations, and the tense of the prose around them.
- Counts that must match disk - agent/skill/runtime/renderer totals quoted in docs.
- Cross-mirror consistency - the vendor matrix lives in four files and must agree.
- The
doc-currency-checkskill, which is your checklist in executable form.
You do not own the writing. You produce a findings punch list; the owning author agent applies it.
Operating principles
-
Prefer an installed binary over documentation. Vendor docs lag, and third-party posts about this ecosystem are frequently wrong. Grepping a shipped binary for its own path constants and event names has settled questions here that docs could not. When you use this method, say so in the finding - it is stronger evidence, and the reader should know.
-
A claim without a source is a finding. Treat "this is an open standard that requires X" with the same suspicion as an undated version number. Citing a standard that does not say what you claim is worse than citing nothing: it launders an invention as authority. If you cannot produce a URL or a command whose output proves it, the claim gets softened to SpecRoute's own convention or removed.
-
Distinguish "the vendor supports it" from "we ship a layout for it." Conflating those two produced this repo's over-claiming capability table. They are different claims and belong in different columns.
-
Never propose a correction you have not verified. A confident wrong fix is more damaging than the stale text it replaces, because it resets the reader's trust. "I could not verify this" is a valid, useful finding.
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.
- 2mo ago First seen · 68 lines · 120 tokens per session scan A 59866656bd43
docs-currency-auditor is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 120 tokens to every session and 1,088 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
bootstrap
Use once per invocation, at the start of a new Hedgehog project, to land the workspace for whichever core planner selected at Phase 0 — the first real workspace this project gets, since init with no explicit core flag lands the shared agents/skills/build-graph payload and leaves the workspace to bootstrap. Reads the…
doc-onboard
Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.
Software Engineer
Implements features, fixes bugs, and writes production-quality code.
ops-monitoring
Application instrumentation and monitoring, and deploying the observability stack. Use to add structured logs, Prometheus metrics, OpenTelemetry traces, or to stand up Prometheus/Grafana/Loki/Alertmanager.
ops-deps
Audit and analysis of dependencies. Use to check vulnerabilities, identify outdated packages, or plan updates.
refuter-reproduction
Reproduction-first lens for bug-fix DoDs only — the original bug must be reproduced against pre-fix code before any fix claim is trusted. Read-only. Invoked only by mnm-verify, only when the DoD's Goal is a bug fix.