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 tonydzi/second-brain-starter-kit --skill canon-revisiongit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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/tonydzi/second-brain-starter-kit/canon-revision)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/canon-revision"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/canon-revision/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/tonydzi/second-brain-starter-kit/canon-revision"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/canon-revision.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 | $0.00090 | $0.01731 |
| Opus 5 | $0.00045 | $0.00865 |
| Sonnet 5 | $0.00018 | $0.00346 |
| Haiku 4.5 | $0.00009 | $0.00173 |
Grade A, and why
canon-revision 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 yesterday.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
canon-revision — revising an always-loaded rules file
The pain: the rules file grows through intake, the structure drifts, and the important parts drown in the middle. The owner's decision (2026-07-22): live in cycles — free growth up to the yellow zone, then a FULL structural revision. This procedure is that revision, battle-tested on CLAUDE.md v2.
Roles: the LLM decides ONLY (a) the mapping of sections into categories, (b) the contents of the TOP block, (c) which sections to fold, plus pinpoint edits from the owner's explicit decisions. The bytes are moved by the SCRIPT, which proves by itself that nothing was lost. Never retype the file by hand.
Step 0 — RECALL + the frame
- Memory: [[claude-md-compression-contract]] (the contract: trigger · directive · clauses · pointer; the two-ends pitfall), [[write-service-files-tight-no-recompress]], [[memory-index-hygiene]] (for MEMORY.md), [[declined-decisions]] (word-level re-compression = declined).
- Thresholds = the defaults in
~/.claude/scripts/claude_md_guard.py(owner, 07-22: yellow 100KB · red 120KB). The truth is the guard's code, not the notes. - A revision = a canon edit → the owner's machine only, in a live session.
Step 1 — Measure BEFORE
python ~/.claude/scripts/claude_md_guard.py + byte size + section counter (^## / ^### ). Record: bytes, sections, md5.
Step 2 — Coordination and safety net
onair.py check --zone canon-skills(for MEMORY.md: memory-index) → clear →onair.py declare --mode exclusive.canon_write_gate.py <file>→ GO + an automatic backup; plus your own*.bak-<date>-revision.- ⚠️ The two-ends pitfall (memory compression-contract): before publishing, verify (a) the md5 of the canon base, (b) the diff of the assembled file against YOUR live file — parallel sessions keep appending through intake.
Step 3 — Assembly (deterministic)
Take references/restructure_claude_md.py (the working sample from 07-22) and adapt the mapping:
- Split by
^##headings; every heading must land in the mapping, an extra/missing one = a loud refusal. - Categories
## §N. <name>+ rules### §N.M <old heading>; bodies verbatim. - The TOP block
## §0. ⭐ TOP-N— the most important rules by the owner's priorities, one line = a rule +→ §X.Y; show the TOP composition to the owner before applying it (or take his previous priorities). - Pinpoint edits — only from the owner's explicit decisions, each through an anchored replace with assert count==1.
- Built-in check: every body is present in the output (BODY LOST = refusal).
What ships with it
2 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.
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.
- yesterday Changed · +2 lines · -14 tokens per session 658a0cede1fd
- 9d ago First seen · 74 lines · 104 tokens per session scan A 0fb1012d51f8
canon-revision is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (6 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,731 once invoked, about $0.0005 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
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…
wiki-mode
Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing.…
wiki-cli
Detect and use the official Obsidian command-line interface for read-only vault access; use for wiki-cli, Obsidian CLI, Obsidian read, Obsidian search, vault transport, which transport, transport detection, backlinks, tags, or Obsidian command line. Mutations always go through the claude-obsidian transaction core.