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/ewebdzine/canonify/plannpx skills add ewebdzine/canonify --skill plangit clone --depth 1 https://github.com/ewebdzine/canonifyWhat 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 | $0.00127 | $0.01295 |
| Opus 5 | $0.00063 | $0.00647 |
| Sonnet 5 | $0.00025 | $0.00259 |
| Haiku 4.5 | $0.00013 | $0.00129 |
Grade A, and why
plan 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 3d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canonify: Plan
The Plan gate of Canonify - the first of three lifecycle gates, all routing through CANONIFY.md. It reads the breadth manifest so the plan is grounded in what the codebase already contains, at a high level, before any architecture is committed.
The three gates are different altitudes, run in order:
- Plan (this skill,
/canonify:plan): the whole landscape -> read everyCANONIFY.mdsummary line -> triage the idea into "what already exists I can reuse" vs. "what's net-new." Breadth. No sub-docs opened. Raises plan quality (architecture). - Build (
/canonify:build): a concrete task -> route to the implicated docs -> load them in full -> canonical pattern + file:line refs. Depth on a slice. Raises implementation fidelity. - Commit (
/canonify:commit): the diff -> route to the same docs -> audit the code against their rules. Raises correctness at the gate.
The Plan gate exists because Build's routing is only as good as the task framing - if the planner doesn't know a capability exists, the task won't mention it, and the route never fires. Plan removes that dependency: it puts the full menu in front of the plan first, so the architecture reuses what's there (an existing service / client / helper / subsystem the idea can stand on) instead of reinventing it.
How to run
-
Read
CANONIFY.mdat the repo root, in full. It is the complete breadth map - one one-line summary per canon across every category the project defines for itself (CANONIFY.mddeclares its own category structure; each category points at a block of docs underdocs/). Read every summary line; the point of the Plan gate is total coverage of the landscape, not a slice. (CANONIFY.mdis authoritative - you should not need to open the per-categoryINDEX.mdfiles to get breadth.) -
Read the idea. It is allowed to be fuzzy - that is what this skill is for. If there is no idea stated at all, ask for one or two sentences of intent ("what are we thinking about building?") before continuing. Don't invent one.
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.
- 3d ago First seen · 66 lines · 127 tokens per session scan A eda543ac57c0
plan is a skill published in the GitHub repository ewebdzine/canonify (23 stars, last pushed 2mo ago), licensed MIT. It adds 127 tokens to every session and 1,295 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…