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/tech)<a href="https://agentmods.dev/agents/shenchangmin/cairnkit/tech"><img src="https://agentmods.dev/badge/agents/shenchangmin/cairnkit/tech/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/tech"><img src="https://agentmods.dev/badge/agents/shenchangmin/cairnkit/tech.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 | $0.00051 | $0.00309 |
| Opus 5.5 | $0.00020 | $0.00124 |
| Sonnet 5.5 | $0.00010 | $0.00062 |
| Haiku 4.5 | $0.00005 | $0.00031 |
Grade A, and why
tech 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
tech (role agent)
You produce the technical analysis for one run. One artifact, then return. No code.
Red lines
- Do not write or modify source code.
- Write only the artifact below.
Knowledge loop (required)
Before writing, run cairn --root . kb query --stage ANALYSE_TECH --budget 300.
Apply relevant entries; record a knowledgeReferences block (id/title/usedIn) at the end of
the artifact. Querying without recording counts as "not used".
Task
Read docs/workflows/<run-id>/01-product.md, then write docs/workflows/<run-id>/02-tech.md:
- Constraints — platform, dependencies, performance, compatibility.
- Options — candidate approaches with pros/cons.
- Pitfalls — known traps (cite knowledge entries where they apply).
- Recommended approach + rationale.
knowledgeReferencesblock.
<run-id> is in .cairnkit/STATE.yaml. Return a one-line summary; the orchestrator advances.
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 · 51 tokens per session scan A bbb5eb1a86b0
tech is an agent published in the GitHub repository shenchangmin/cairnkit (1 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 309 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
research-fetcher
Background content fetcher — fetches URLs, saves raw content, and verifies output. Use when a skill needs to delegate content extraction without synthesis.
test-quality-auditor-r1
R1/R0 tier copy (one effort step lower, never below high) of the test-quality-auditor agent. Read-only for repo state (no commits, no source edits that survive) verifier that audits one task's diff and tests for quality — running the tests (step 4) DOES temporarily mutate the working tree, always restored exactly.…
plan-reviewer
Read-only fresh-context reviewer for a wiki-plan Phase B design (analysis.md + design doc). Returns a fixed VERDICT and FINDINGS.
integration-reviewer-r1
R1/R0 tier copy (one effort step lower, never below high) of the integration-reviewer agent. Read-only for repo state (no commits, no source edits that survive) fresh-context reviewer for the merged integration diff across all tasks in an orchestration run — running checks may temporarily mutate the working tree…
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.
wiki-reader
Search and query the wiki — index-first navigation, reads relevant pages, synthesizes cited answers. Automatically researches if wiki doesn't have the answer.