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 skills add product-on-purpose/agent-skills-toolkit --skill askit-standards-watchgit clone --depth 1 https://github.com/product-on-purpose/agent-skills-toolkitWrote 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/product-on-purpose/agent-skills-toolkit/askit-standards-watch)<a href="https://agentmods.dev/skills/product-on-purpose/agent-skills-toolkit/askit-standards-watch"><img src="https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-standards-watch/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/product-on-purpose/agent-skills-toolkit/askit-standards-watch"><img src="https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-standards-watch.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 | $0.00075 | $0.01702 |
| Opus 5 | $0.00037 | $0.00851 |
| Sonnet 5 | $0.00015 | $0.00340 |
| Haiku 4.5 | $0.00007 | $0.00170 |
Grade A, and why
askit-standards-watch 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 11d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
askit-standards-watch
Purpose
STANDARD.md sec 6 states, as normative text, that where agentskills.io evolves the Universal tier MUST track it; higher tiers remain this Standard's domain. Tracking is only auditable against a recorded starting point. This skill owns that starting point (foundation/claims/upstream-pin.json), detects when the upstream has moved away from it, maps each delta to the checks it lands on, and produces a proposal. It never applies one.
When to use
When someone asks whether the upstream spec has changed, before cutting a Standard MINOR, on a periodic governance sweep, or when re-pinning the upstream revision after an ADR is accepted.
The one hard rule
This skill proposes. A human decides. Nothing here edits a check module, STANDARD.md, an existing ADR, or the pin.
The Standard grows only by ADR with the warn-first burndown of sec 7.7 (a new or tightened requirement ships as a warn for one MINOR, then becomes an error). A watcher that edited a check would convert a governed decision into a silent one, which is the single thing that would make the gate untrustworthy. The deterministic half is write-incapable by construction: scripts/lib/standards-watch.mjs and scripts/standards-watch.mjs import only readFileSync from node:fs and emit everything to stdout, and a test fails the build if any write API appears in either file. Your obligation is to keep the same discipline in the steps below.
Procedure
1. Run the watch
npm run standards-watch
Exit 0 means unchanged or cosmetic-only; 1 means a human must look; 2 is a refusal (fetch failed, extraction failed, no pin). A refusal is never a pass. Add --json for the machine report, --snapshot-dir <dir> to run offline against a local mirror.
If it exits 0, stop. Report "unchanged since <verified date>" and offer to refresh the verification date (step 5). Do not invent work.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/anti-1-apply-the-change-directly.md 2.6 KB
- examples/golden-1-upstream-unchanged.md 1.8 KB
- examples/golden-2-real-upstream-delta.md 3.1 KB
- examples/golden-3-new-required-field.md 3.2 KB
- examples/pin-historical-2026-05-15.json 11 KB
- README.md 815 B
- references/materiality-rubric.md 4.6 KB
- references/pin-format.md 5.2 KB
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.
- 11d ago First seen · 87 lines · 75 tokens per session scan A bf4c1847a9fb
askit-standards-watch is a skill published in the GitHub repository product-on-purpose/agent-skills-toolkit (2 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 1,702 once invoked, about $0.0004 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
modelchk
Size a task's run before spending it: the cheapest sufficient capability tier (fast, standard, frontier) and the reasoning effort within it, on a neutral scale that binds to whatever levels the model exposes. Use when work seems over- or under-powered, costly, ambiguous, or high-risk, or asks which model class and how…
autobahn
Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt, never the risky input. Use when a task includes stealth, scraping, privacy, IP, policy, licensing, security, or…
re0-release
Walk a pending change through this repo's shipping and releasing checklist end to end, then tag and publish once confirmed. User-invoked: run it when you've decided to ship.
ssotize
Audit and consolidate a fact that's scattered across places into one canonical source, after approval, and replace the rest with references. Use when asked to find duplication, check consistency, locate the source of truth, deduplicate, consolidate, unify, or establish SSOT across artifacts or platforms. Starts…
dedash
Remove em-dashes and the dashes standing in for them from a user-owned scope, reading each occurrence in context and choosing the punctuation or wording that fits.
feynman
Press a decision you just made until you can explain it to a skeptic in your own words, or surface the gap where you can't. The Feynman test aimed at a choice: understanding is cheapest to fake the moment after you decide, so a fresh critic presses for what you can't actually explain. Use right after picking an…