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 ewebdzine/canonify --skill import-canongit clone --depth 1 https://github.com/ewebdzine/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/import-canon)<a href="https://agentmods.dev/skills/ewebdzine/canonify/import-canon"><img src="https://agentmods.dev/badge/skills/ewebdzine/canonify/import-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 | $0.00136 | $0.01540 |
| Opus 5 | $0.00068 | $0.00770 |
| Sonnet 5 | $0.00027 | $0.00308 |
| Haiku 4.5 | $0.00014 | $0.00154 |
Grade A, and why
import-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 7d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Import canons (from another project)
Canonify's bulk seeding from a sibling project gate. Several repos that share a platform (e.g. Composite C1) each re-document the same patterns; this gate lets you take the canons one project already wrote and stand them up in THIS repo without re-authoring from scratch - and without the trap of a blind copy.
It is /canonify:create-canon run over a list, seeded from existing canons instead of a blank
read of the code. The crucial difference from cp -r: every canon cites file:line into a
specific repo and carries a verified: <sha> for that repo's HEAD. Copy the source files in and
those citations point at the OTHER project's paths and a foreign commit - they are wrong, and
/canonify:doctor will flag the whole batch. So each source canon is used only as a skeleton +
checklist (its topic, sections, the patterns/gotchas it documents); the claims are re-proved
against this repo's code. Sibling of /canonify:kickoff's scan-and-seed, which seeds from a code
scan instead of from another project's canons.
How to run
-
Get the source list. The user points at the source canons - a folder (
<projectA>/docs/<area>/), a single canon file, or an explicit list of paths. Enumerate the concrete set of source.mdcanons (read the folder'sINDEX.mdif present). Confirm the list in one line. If nothing is named, ask which folder or canons to import. -
Place each into THIS repo's taxonomy. For each source canon, decide its destination category from this repo's
CANONIFY.mdblocks + existingdocs/folders - the same placement logic ascreate-canon. Do NOT mirror the source project's folder layout blindly; map into the categories this repo already uses (create a category only when none fits). Destination isdocs/<category>/<topic>.md. -
Dedup before importing. For each source canon, check whether this repo already has a canon covering that area (route via
CANONIFY.mdsummaries, like build/commit/update-canon):- Already covered here -> SKIP the import; note it. If the source canon clearly carries
something this repo's version lacks, suggest
/canonify:update-canoninstead of a second doc. - Not covered -> import it (steps 4-6).
- Already covered here -> SKIP the import; note it. If the source canon clearly carries
something this repo's version lacks, suggest
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.
- 7d ago First seen · 98 lines · 136 tokens per session scan A f0998634ba88
import-canon is a skill published in the GitHub repository ewebdzine/canonify (23 stars, last pushed 2mo ago), licensed MIT. It adds 136 tokens to every session and 1,540 once invoked, about $0.0007 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.