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 commands/saigonxiii/evc/canon-diffgit clone --depth 1 https://github.com/SaigonXIII/evcWhat 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 | $0.00034 | $0.00858 |
| Opus 5 | $0.00017 | $0.00429 |
| Sonnet 5 | $0.00007 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
canon-diff 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canon Diff
Show recent changes to brand/canon-rules.json — what was added, removed, or modified. Backed by brand/canon-history/CHANGELOG.md which is auto-maintained by the canon-changelog hook on every session stop.
Usage
/project:canon-diff # changes since last snapshot
/project:canon-diff 7d # last 7 days
/project:canon-diff 30d # last 30 days
/project:canon-diff 2026-01-01 # since a specific date
/project:canon-diff restore [stamp] # rollback to a prior snapshot (confirm required)
Steps
1. Check changelog exists
Read brand/canon-history/CHANGELOG.md. If missing, print:
No canon history yet. The canon-changelog hook will start tracking changes on the next edit.
And exit.
2. Parse args
- No arg → show all entries since the most recent snapshot
[N]d→ show entries from the last N daysYYYY-MM-DD→ show entries since that daterestore [stamp]→ enter restore flow (see step 5)
3. Extract relevant entries
Parse the CHANGELOG.md. Each entry is a markdown section beginning with ## YYYY-MM-DD HH:MM — canon modified and ending at ---.
Filter entries by the date range from step 2.
4. Render output
Print entries in this format:
CANON CHANGELOG — [filter description]
════════════════════════════════════════════════════
[N] changes across [M] entries
───────────────────────────────────────────────────
2026-04-05 14:32 — canon modified
Added:
banned_phrases: "crypto casino"
framing_red_flags: "web3 for all"
Removed:
defunct_partners: "OldBrand"
Modified:
required_language.company_anchor:
OLD: "Acme does X"
NEW: "Acme does X for Y"
───────────────────────────────────────────────────
[next entry...]
At the bottom show a summary:
Summary:
Entries: [N]
Adds: [N] Removes: [N] Modifications: [N]
Latest snapshot: brand/canon-history/snapshots/canon-[stamp].json
5. Restore flow (optional)
If the user passed restore [stamp]:
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.
- 2d ago First seen · 117 lines · 34 tokens per session scan A 3b7a03c25831
canon-diff is a command published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 858 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 2026-08-30.
Other commands, from other repositories
review-tool
Research a tool or product for skill-gap, architecture, and verb-fit per the Anatomy framework.
setup
First-run setup — replace the fictional company and authors with yours.
content-status
Scan all content directories and report status of drafts, ideas, and published content.
draft-blog
Scaffold a blog post with proper structure, voice, and frontmatter.
review-content
Review content for brand alignment, lead placement, bio consistency, and proof points.
voice-check
Check a draft against the author's voice profile and flag deviations.