Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ewebdzine/canonify/plugin install canonifyWrote 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/ewebdzine/canonify/update-canon)<a href="https://agentmods.dev/skills/ewebdzine/canonify/update-canon"><img src="https://agentmods.dev/badge/skills/ewebdzine/canonify/update-canon.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 | $0.00120 | $0.01501 |
| Opus 5 | $0.00060 | $0.00750 |
| Sonnet 5 | $0.00024 | $0.00300 |
| Haiku 4.5 | $0.00012 | $0.00150 |
Grade A, and why
update-canon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update a canon
Canonify's maintenance gate. Where /canonify:create-canon authors a new canon from a
file/service/element, this gate edits an existing one: you discovered something while coding -
a footgun, a sharper rule, a pattern that drifted - and you want it captured now, in flow, without
hand-editing markdown. Describe the update; this gate finds the right canon, decides whether the
knowledge is already there, and either tells you it's covered or adds it cleanly.
It routes off CANONIFY.md exactly like build/commit (match the summary lines), and writes to the
same house-style as create-canon (${CLAUDE_PLUGIN_ROOT}/templates/doc-style.md): cite every claim
file:line, ASCII punctuation, terse and project-specific.
How to run
-
Get the update. The user describes what they learned. If they didn't say it, ask once: "what did you discover, and which area does it touch?" Don't guess the content.
-
Route to the canon. Find which existing canon owns this. Same selector as build/commit: read
CANONIFY.md, match the update against the one-line summaries. Usually it's inferable from the file in play (working in form code -> the FormBuilder canon) or named outright. Confirm the target in one line. If two canons could own it, ask which. If NO canon covers the area at all, stop and hand off: this gate edits existing canons - say so and suggest/canonify:create-canon. -
Load the canon + re-read the cited code. Read the target canon in full, and re-read the specific code it cites for the affected section. You need both: the doc (to dedup against) and the live code (so any addition is cited to a real
file:lineand any "is it still true" check is against reality, not just the old prose). -
Triage the update against the canon - the dedup check. This is the core. Decide which case:
- Already covered, still accurate -> Don't edit. Tell the user where it's documented (section
- the
file:lineit cites). Offer a sharpen only if the wording is genuinely weak (buried, vague, easy to miss); otherwise say it's covered and stop.
- the
- Partially covered or stale -> Propose a revision: tighten the rule, add the missed nuance, or correct what no longer matches the code. Show before -> after for the changed lines.
- Not covered -> Draft the addition in house-style, cited to
file:line, placed in the right section by kind: a footgun -> Gotchas; a new or sharper rule -> The pattern; a new call site -> Recipes; a config key -> Configuration / API surface.
- Already covered, still accurate -> Don't edit. Tell the user where it's documented (section
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 · 100 lines · 120 tokens per session scan A c48a83b30b42
update-canon is a skill published in the GitHub repository ewebdzine/canonify (23 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 1,501 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…