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 philipyaz/cos --skill second-brain-lintgit clone --depth 1 https://github.com/philipyaz/cosWrote 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/philipyaz/cos/second-brain-lint)<a href="https://agentmods.dev/skills/philipyaz/cos/second-brain-lint"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/second-brain-lint.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 | $0.00129 | $0.02867 |
| Opus 5 | $0.00064 | $0.01434 |
| Sonnet 5 | $0.00026 | $0.00573 |
| Haiku 4.5 | $0.00013 | $0.00287 |
Grade A, and why
second-brain-lint 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second Brain — Lint (knowledge integrity pass)
A scheduled integrity pass over the domain-split wiki. This is not an MCP route —
it is a periodic health check. It runs over the three wiki trees — work/wiki,
life/wiki, and shared/wiki — independently, and reports issues with actionable
fixes. The vault is knowledge-only: this lint never writes the board (it has no board
access). It auto-fixes the safe, deterministic issues itself and proposes the
judgment or destructive ones — see the auto-fix policy below.
Run every check below for each domain tree, applying the safe auto-fixes as you go, then present one consolidated report (grouped by domain and severity) that separates what was auto-fixed from what is proposed.
Auto-fix policy — repair the safe, propose the rest
Lint does not just flag; it fixes what is safe to fix automatically and proposes everything that needs judgment. Two tiers:
AUTO-FIX (apply the edit, then record it in the report) — only when the repair is deterministic and unambiguous:
- Filename ≠ H1 → rewrite the H1 to match the filename (the filename is what
[[wikilinks]]resolve to, so it is canonical). - Broken
[[wikilink]]with a single unambiguous target → repoint it via an exactaliases.mdmapping or a one-to-one rename (e.g.[[Jane]]→[[Jane Doe]]). If the link is a same-page section reference that — per the reinforce-before-spawn doctrine — should not get its own page, de-link it to plain text instead. - A genuinely homeless page → add it to the index under
## Unfiled(additive, never lossy). Choosing its real theme is a proposal, not an auto-fix.
PROPOSE ONLY (never auto-apply — describe the fix, leave the page untouched) — anything destructive, lossy, or a judgment call:
- Bloat merges / prunes (Check 9), page deletions, folding one page into another.
- Contradictions / stale claims (Check 8) — re-synthesis is a judgment rewrite.
- Cross-domain moves, orphan resolution, and strong-index theme placement.
- Stray task checkboxes — these signal an item that belongs on the board; lint has no board access, so it flags the item for routing rather than silently deleting the action.
- Legacy
priorities.md/reminders/— flag for removal; never delete unread.
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 · +69 lines · +14 tokens per session fd32a3ec7bd9
- 8d ago First seen · 145 lines · 115 tokens per session scan A 93f7f06d3f23
second-brain-lint is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed today), licensed MIT. It adds 129 tokens to every session and 2,867 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 2026-08-31.
Other skills, from other repositories
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
wiki-export
Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…
wiki-query
Answer a question using ONLY the existing wiki vault as the knowledge base — no web search, no general LLM knowledge. Reads hot.md first (cheap recent context), then catalog.md to navigate, then drills into specific pages, then optionally semantic-searches the wiki, and synthesizes an answer with citations. Use when…
wiki-fold
Roll up the wiki's journal.md entries into structured fold pages — like 2^k log compaction. Reads the last 2, 4, 8, 16... entries and writes a fold page that summarizes them by extractive summarization (no invention), with backlinks to children. Idempotent at the structural level — re-running with the same window…
wiki
Bootstrap or check a Karpathy-style "LLM wiki" structure inside an Obsidian vault — a self-maintaining knowledge base where pages reference each other and the LLM keeps it tidy. Sets up catalog.md (curated page catalog), journal.md (append-only operation history), hot.md (recent-context cache), and overview.md…