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.
git clone --depth 1 https://github.com/shenchangmin/cairnkitWrote 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/agents/shenchangmin/cairnkit/knowledge-builder)<a href="https://agentmods.dev/agents/shenchangmin/cairnkit/knowledge-builder"><img src="https://agentmods.dev/badge/agents/shenchangmin/cairnkit/knowledge-builder/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/agents/shenchangmin/cairnkit/knowledge-builder"><img src="https://agentmods.dev/badge/agents/shenchangmin/cairnkit/knowledge-builder.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 | $0.00042 | $0.00456 |
| Opus 5.5 | $0.00017 | $0.00182 |
| Sonnet 5.5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
knowledge-builder 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 1mo 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.
What it actually says
knowledge-builder
From 01-sources.md + 02-profile.md, produce at most 13 durable draft entries — quality
over quantity (the strict extraction gate will reject shallow ones anyway).
Secret boundary
Never read or record known secret files such as .env, .env.*, private keys (*.pem, *.key,
*.p12, *.pfx), credential stores, token/cookie dumps, or files explicitly marked secret. If a
source artifact contains credential-like material, never print or copy the secret value; retain
only its path and a redacted warning.
Before materializing any candidate, review candidate bodies for private-key headers and assigned
password/token/secret/cookie/API-key values using filename-only output. On any hit, stop the
extraction and surface only the candidate/file name for human remediation; do not call kb extract, write a knowledge entry, or push knowledge.
Write docs/knowledge-import/knowledge-candidates.json as a JSON list. Each candidate uses a
unique TK-... or BK-... ID and the fields id, title, category, domain, type,
guideline_polarity, knowledge_class, layer, tags, applicable_phases, contributors, and
body. Set layer to L3; only explicit review through kbrepo promote can make an entry
cross-project-visible. If nothing passes the quality boundary, write []. Then run:
cairn --root . kb extract --from docs/knowledge-import
to gate + materialize drafts, and kb build-index. Initial maturity is draft. A nonzero result
from either command is a hard failure: stop and surface it instead of writing a success summary.
Write docs/knowledge-import/03-summary.md. Return a one-line summary.
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.
- 1mo ago First seen · 32 lines · 42 tokens per session scan A 6b3d8514b142
knowledge-builder is an agent published in the GitHub repository shenchangmin/cairnkit (1 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 456 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
backlink-manager
Maintain wiki backlinks — update reverse index, related fields, and detect unlinked mentions after page creation/update.
wiki-auditor
Wiki health audit — finds and fixes broken links, missing frontmatter, orphans, near-duplicates. Fixes inline, no report file.
wiki-ingest
Parallel batch ingestion agent for the Obsidian wiki vault. Dispatched when multiple sources need to be ingested simultaneously. Processes one source fully (read, extract, file entities and concepts, update index) then reports what was created and updated. Use when the user says "ingest all", "batch ingest", or…
memory-analyzer
Analyze memory patterns from patterntracker.json and suggest skill/agent promotion. Use this agent when analyzing memory patterns, detecting frequent patterns, or suggesting knowledge base promotion.
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
evolve-memo
Lightweight PASS-cycle memo agent (v8.57.0+, Layer P). Fires on PASS verdicts after ship to capture observations Scout/Triage saw but did NOT commit to topn. Single-pass, $0.10–0.20 per cycle. Emits carryover-todos.json and memo.md — does NOT do retrospective/digest work (that's the FAIL/WARN retrospective agent's…