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 agentmods add skills/mhashim6/kauri/check-stalenessnpx skills add mhashim6/kauri --skill check-stalenessgit clone --depth 1 https://github.com/mhashim6/kauriWrote 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/mhashim6/kauri/check-staleness)<a href="https://agentmods.dev/skills/mhashim6/kauri/check-staleness"><img src="https://agentmods.dev/badge/skills/mhashim6/kauri/check-staleness.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.00365 |
| Opus 5 | $0.00018 | $0.00182 |
| Sonnet 5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
check-staleness 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 6d 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
Check Decision Staleness
Run a staleness check on all active Kauri decisions and help the user resolve any stale records.
Steps
-
Run the check: Use
kauri_checkto scan all active records. -
For each stale record:
- Use
kauri_showto see the full decision content. - Assess whether the decision is still valid given the current code state.
- Explain to the user what changed and why the record was flagged.
- Use
-
Resolve each stale record by asking the user to choose:
- Still valid: Use
kauri_validatewith verdictstill_validto refresh the timestamp. - Needs updating: Use
kauri_recordwithsupersedesto create a new decision replacing the old one. - No longer relevant: Use
kauri_validatewith verdictdeprecate.
- Still valid: Use
What "stale" means
A record is stale when:
- Time-based: More than
ttl_dayshave passed since last validation (default 90 days). - File-based: A file associated with the record has changed content since the last validation.
Stale does NOT mean wrong — it means "please review." The decision might still be perfectly valid.
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.
- 6d ago First seen · 36 lines · 36 tokens per session scan A 4ab5c89d223e
check-staleness is a skill published in the GitHub repository mhashim6/kauri (5 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 365 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
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
reminder
Set reminders and manage todos with natural language. Uses built-in cron scheduling, no external service needed.
workflow-chain
Chain multiple skills and actions into named workflows with error handling and conditional branching.
tts-voice
Convert text to natural speech audio. Uses Edge-TTS (free) or OpenAI TTS. Excellent Chinese voice support.
excel-author
Create and edit Excel (.xlsx) workbooks with openpyxl. Supports formulas, charts, formatting, and data analysis.
image-gen
Generate images via DALL-E, Stable Diffusion, or free alternatives. Supports multi-channel delivery.