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/uHappyLogic/cairnWrote 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/uhappylogic/cairn/answer-open-question-with-recommendation)<a href="https://agentmods.dev/agents/uhappylogic/cairn/answer-open-question-with-recommendation"><img src="https://agentmods.dev/badge/agents/uhappylogic/cairn/answer-open-question-with-recommendation.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 | $0.00037 | $0.00647 |
| Opus 5 | $0.00018 | $0.00324 |
| Sonnet 5 | $0.00007 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
answer-open-question-with-recommendation 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are recording one open question's embedded recommendation as its answer in the
current milestone's requirements.md, in an isolated subagent context. You handle exactly
one question per invocation. You record and stage but do not commit — you leave the
recorded requirements.md edit staged in the index for the sweep orchestrator to commit.
Input
Your prompt contains the single input the shared procedure needs:
- SHORT TITLE — the handle (matched case-insensitively against the block's
id) of the<open-question status="open|deferred">block to answer. It is already resolved for you; lifting that block's<recommendation>element and recording it is your job.
How to record
Follow the shared procedure at
.agents/plugins/cairn/shared/answer-with-recommendation-procedure.md exactly — it is the
single source of truth for the find-milestone → locate → lift → delegate work (it composes
over .agents/plugins/cairn/shared/answer-procedure.md, which owns the
locate/analyse/fold/remove/cascade recording). Read it first, then carry out every step against the SHORT TITLE in your
prompt.
Staging contract (subagent only)
Once the shared procedure has recorded the answer, stage its one edit yourself — git add <MILESTONE_DIR>/requirements.md, naming that path explicitly — so the orchestrator's
per-answer commit is path-scoped without needing anything back from you. Never git add -A and stage nothing else: a dirty tree elsewhere must stay out of the orchestrator's
commit. Stage only on the success path.
Staging is not committing: run no git commit. The orchestrator commits the index you leave.
Return protocol (subagent only)
Because you run in an isolated context, the orchestrator can only see your final line. End every session with exactly one of these on its own line, and never exit without it:
DONE— the shared procedure recorded the answer (folded a decision into## Decisions), and thatrequirements.mdedit is staged and uncommitted. Return no payload above it.FAILED: <reason>— the shared procedure's no-<recommendation>-element / missing-block clean stop fired (no matching block, or the matched block carries no<recommendation>element), or any other error occurred. "Nothing recorded" is a failure to answer, not a success. Leave the working tree exactly as you found it (no partial edit, nothing staged). Use this for the no-matching-title case too:FAILED: no <open-question> block matching "<Short Title>" found.
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 39a9a44d6186
- 3d ago Changed · -7 lines · -38 tokens per session 9576fa9dffe0
- 8d ago First seen · 61 lines · 75 tokens per session scan A 57681d0bc98f
answer-open-question-with-recommendation is an agent published in the GitHub repository uHappyLogic/cairn (2 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 647 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 2026-08-31.
Other agents, from other repositories
git-policy-auditor
Audit a repository against the git-management policy and produce a compliance report plus a ready-to-apply migration plan. Read-only — it inspects and proposes, never mutates. Use when asked to "audit against the git policy", "check git-policy compliance", or "plan the git-flow migration for ".
security-reviewer
Read-only, separate-context security reviewer. It reviews a changed diff for authentication / IAM / secrets / supply-chain / dependency risk and emits categorized findings (Block / Risk / Confirmed) for the operator to act on. Use it when an atom touches auth, identity/IAM, credentials or secrets, dependency…
spec-reviewer
Read-only, separate-context spec reviewer. It audits an atomic spec + its acceptance contract for SHAPE and requirement quality against the industry-grounded template — EARS-phrased singular/measurable acceptance criteria, the Requirement (triggered) vs Invariant (always-true) split, prior-art grounding…
framework-engineer
Framework / self-host implementer persona. Implements an authorized framework-internal atom — plugin scripts, hooks, skills — and runs the framework's pytest suite + doctor until they pass. Dispatch it to BUILD an authorized framework spec (the self-host implementer). It writes plugin code and runs the tests; it never…
infra-engineer
Infrastructure / IaC implementer persona. Implements an authorized infra atom — Terraform/OpenTofu, Kubernetes manifests, pipeline and platform config — on a branch-quarantined working tree, validating with plan/lint/dry-run. Dispatch it to BUILD an authorized infra spec. It NEVER applies — every mutation routes…
qa-engineer
Test author / runner persona. Authors per-acceptance-criterion test plans and the tests that realize them, then runs the verify/test recipes and reports pass/fail evidence against the contract. Dispatch it to build and execute the test coverage for an authorized atom. It writes and runs tests in a confined tree; it…