Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRoutenpx agentmods add skills/enovatr-labs/specroute/doc-currency-checkWrote 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/enovatr-labs/specroute/doc-currency-check)<a href="https://agentmods.dev/skills/enovatr-labs/specroute/doc-currency-check"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/doc-currency-check/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/enovatr-labs/specroute/doc-currency-check"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/doc-currency-check.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 | $0.00106 | $0.01579 |
| Opus 5 | $0.00053 | $0.00790 |
| Sonnet 5 | $0.00021 | $0.00316 |
| Haiku 4.5 | $0.00011 | $0.00158 |
Grade A, and why
doc-currency-check scanned grade A with 1 finding 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 12d 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.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls -d .claude/skills/*/ | wc -l # skill count Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Currency Check
SpecRoute's value proposition is being correct about other people's tools. That makes staleness a correctness bug, not a cosmetic one. This skill finds the classes of rot that have actually bitten this repo before.
Why these specific checks
Every check below exists because that exact failure happened here:
- A vendor replaced a config format and 19 files kept describing the dead one.
- A half-applied migration left a contract declared in one file and contradicted in three.
- An EOL date passed and ten files still described it in the future tense.
- A capability table claimed support the runtime layouts didn't ship.
- A fabricated external "standard" was cited as the authority for a real change.
Step 1: Scope
If given an area, run only that section. Otherwise run all six checks below.
Step 2: Vendor facts (needs internet)
For each vendor in the matrix, check the official docs - not blog posts, which are frequently wrong about this ecosystem:
- Does the config path still exist? Has the file format changed?
- Have hook event names, counts, or handler types changed?
- Have frontmatter contracts gained or lost fields?
- Is the product still called what we call it?
Prefer an installed binary over documentation when one is available. Docs lag and third-party sources contradict each other. Grepping a vendor's shipped binary for its own path and event-name constants has settled several questions here that docs could not:
command -v codex gemini cursor
# then grep the resolved binary for the constants you care about
Record the evidence for each answer, not just the answer.
Step 3: Version anchors
rg -n "v?[0-9]+\.[0-9]+(\.[0-9]+)?" --glob '*.md' --glob '!.git/**' | grep -iE "as of|current|stable|version|since"
Any anchor naming a specific vendor release is a rot candidate. Two failure shapes:
- Overtaken - "current stable vX" where X is now several releases behind.
- Load-bearing - "requires vX+" where the feature is now unconditional.
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.
- 12d ago First seen · 134 lines · 106 tokens per session scan A 4dcdd41680e9
doc-currency-check is a skill published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,579 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
file-a-task
File work into nohuman (taskadd) and check on it (taskstatus) via the nohuman MCP bridge, instead of doing the work inline.
merge-aliases
Folds two surface names for the same backend system into one canonical entity, keeping every original mention individually retrievable, and refuses to merge pairs that only share spelling.
anchor-and-lock
Consults a check that sits outside the loop system before finalizing any decision the frozen facts bear on, and refuses every attempt by a loop to rewrite a node marked frozen, regardless of how convergent the loop's own reasoning looks.
query-graph
Loads schema.sql into a local SQLite file, then answers availability and provenance questions against the nodes/edges tables with real SQL instead of re-reading source material.
build-subgraph
Traverses a full graph and returns a bounded subgraph around one target node -- its depth-bounded dependencies plus any disputed claims attached to it -- while proving everything else was left out.
arbitrate-collision
Detects when two loops have proposed conflicting writes to the same node and field at close to the same time, applies a stated priority rule to accept exactly one, and records the rejected write with the reason it lost.