triage-knowledge

triage-knowledge is a skill for Claude Code from Curt-Park/autology. It costs 43 tokens per session (501 once invoked), scanned A, original, MIT.

A process for checking project documentation against recent decisions, changes, and discoveries, then classifying the relevant knowledge as already documented or new.

In plain words
What is it for?
Use it after commits, refactors, or important decisions to find matching files, identify missing knowledge, and suggest links between documentation topics.
Why use it?
It helps keep documentation in sync after significant work and shows how related notes are connected.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the autology plugin — 6 skills, 2 commands, 1 hook shipped together

Good fit Use it after commits, refactors, or important decisions to find matching files, identify missing knowledge, and suggest links between documentation topics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/curt-park/autology/triage-knowledge
Install

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.

Any agent
npx skills add Curt-Park/autology --skill triage-knowledge
Clone the repo
git clone --depth 1 https://github.com/Curt-Park/autology

Made for: Claude Code.

Or install autology, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 1 hook.

Wrote 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.

agentmods badge for triage-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/skills/curt-park/autology/triage-knowledge/github.svg)](https://agentmods.dev/skills/curt-park/autology/triage-knowledge)
Your own site
<a href="https://agentmods.dev/skills/curt-park/autology/triage-knowledge"><img src="https://agentmods.dev/badge/skills/curt-park/autology/triage-knowledge/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.

agentmods 80×15 button for triage-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/skills/curt-park/autology/triage-knowledge"><img src="https://agentmods.dev/badge/skills/curt-park/autology/triage-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00501
Opus 5 $0.00022 $0.00251
Sonnet 5 $0.00009 $0.00100
Haiku 4.5 $0.00004 $0.00050

Measured 9d ago against content hash 0a7171f70bd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

triage-knowledge 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 9d 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.

skills/triage-knowledge/SKILL.md · 67 lines

What it actually says

Overview

Scan docs/ against conversation context or an action summary. Classify each knowledge item as existing or new, and return topology hints (connected nodes, shared tags) so sync and capture can use them during execution.

Process

1. Extract knowledge items from context

From conversation or action summary, identify:

  • Decisions made, conventions established, components changed, patterns discovered

2. Search docs/ for each item

For each item:

  • Grep docs/ for keywords, titles, tags
  • Read matched files to confirm relevance

3. Build topology hints

For matched nodes:

  • Extract wikilink connections ([[target]] patterns)
  • Identify nodes sharing tags
  • Flag hub/orphan status

For unmatched new items:

  • Suggest related existing nodes based on tags or content overlap

4. Return classified list

Output Format

Autology — Triage Results

Existing (→ sync)

  • docs/foo.md — matches [item description] Connected: [[bar]], [[baz]] | Tags: arch, api | Hub (5 links)
  • docs/qux.md — matches [item description] Connected: [[foo]] | Tags: convention | Orphan-adjacent

New (→ capture)

  • [item description] — no matching node Suggested relations: [[foo]], [[bar]] (shared tags: architecture)
  • [item description] — no matching node Suggested relations: none

If no existing docs match any items, use empty-state format:

Autology — Triage Results

No existing matches found. All items classified as new.

New (→ capture)

  • [item description] — no matching node Suggested relations: [[foo]] (shared tags: architecture)

Common Mistakes

Mistake Fix
Judge relevance by keyword match alone Read the file to confirm actual relevance
Omit topology hints sync/capture rely on connected/suggested relations — always include
Ignore implicit relations Check tags and content overlap even without wikilinks
Files

What ships with it

3 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.

Changes

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.

  1. 9d ago First seen · 67 lines · 43 tokens per session scan A 0a7171f70bd3

Subscribe to this mod's changes

triage-knowledge is a skill published in the GitHub repository Curt-Park/autology (24 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 501 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.

Related

Other skills, from other repositories

mama-context

Always-on background context injection from MAMA memory. Automatically surfaces relevant decisions when you work on code, without explicit invocation.

jungjaehoon-lifegamez/MAMA · 28 tokens

mama-install

Install MAMA OS and follow its self-teaching CLI until the first report is confirmed.

jungjaehoon-lifegamez/MAMA · 22 tokens

vault

Search, read, write, and manage files in the Kept conversation vault. Use when the user asks about past conversations, wants to save notes, needs to find specific content, or wants to organize their vault.

egroup-labs/kept · 45 tokens

kb-session-review

Review this session's knowledge base usage. Use when the user asks whether the KB was updated, what was captured, if anything was missed, or wants a session retrospective on knowledge capture quality.

mrosnerr/open-zk-kb · 42 tokens

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…

AgriciDaniel/claude-obsidian · 81 tokens

memory-audit-pattern-extraction

A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.

Dataojitori/nocturne_memory · 48 tokens