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 uHappyLogic/cairn --skill answer-open-question-with-alternativegit 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/skills/uhappylogic/cairn/answer-open-question-with-alternative)<a href="https://agentmods.dev/skills/uhappylogic/cairn/answer-open-question-with-alternative"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/answer-open-question-with-alternative/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/skills/uhappylogic/cairn/answer-open-question-with-alternative"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/answer-open-question-with-alternative.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 | $0.00031 | $0.02067 |
| Opus 5 | $0.00015 | $0.01033 |
| Sonnet 5 | $0.00006 | $0.00413 |
| Haiku 4.5 | $0.00003 | $0.00207 |
Grade A, and why
answer-open-question-with-alternative 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
answer-open-question-with-alternative
Records a named <alternative> from one open question's embedded analysis as its answer
inline, in the current conversation — never in a subagent — so the recording reasoning
(which block was resolved, which alternative was chosen, what decision was folded in, what
cascaded) stays in context for follow-up.
This is the sibling of answer-open-question-with-recommendation: same recommend-sweep
annotations, same recording core, but the answer is the <alternative> you name by its
id rather than the one <recommendation> the sweep picked — which lets you record a
decision that overrides the recommendation, or resolve a question the sweep left genuinely
tied. There is deliberately no batch or agent form of this skill; to record every
recommendation-bearing question at its recommended option unattended, use
/answer-all-open-questions-with-recommendation.
Invocation
/answer-open-question-with-alternative <Short Title>. <Alternative Id>
Split the argument on the first . — exactly as answer-open-question does. Everything
before it is <Short Title> (the question handle); everything after it is <Alternative Id>
(the id of the <alternative> to record). Trim surrounding whitespace from both halves.
<Short Title>must match (case-insensitive, against the block'sid) an existing<open-question status="open|deferred">block that the/recommend-all-open-questionssweep has already annotated with<alternative>elements.<Alternative Id>must match (case-insensitive, against theidattribute) one of that block's embedded<alternative id="...">elements.
The procedure resolves the current milestone itself, so nothing needs to be looked up first.
Workflow
1. Find the current milestone
Follow .agents/plugins/cairn/shared/get-current-milestone.md to resolve <MILESTONE_DIR>. Never use a hardcoded
task-list path. Hold <MILESTONE_DIR> — you need it for the delegated recording and the
commit.
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 · +3 lines 25a9d7e2af24
- 2d ago Changed · -3 lines 54e4238b15d0
- 4d ago Changed · -45 lines · -60 tokens per session 4e271773e46a
- 9d ago First seen · 197 lines · 91 tokens per session scan A fea828ed9e97
answer-open-question-with-alternative is a skill published in the GitHub repository uHappyLogic/cairn (2 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 2,067 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 skills, from other repositories
debt-ops-add
Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…
plan-task
Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.
dont-leave-me
A stop-before-finishing checklist for an agent that checks whether requested work, changed files, verification, and cleanup have actually been handled.
log
Capture front door. Logs 1..N observations as card files at docs/work/{ID}.md (BUG / DEBT / GAP), gateway-inline — no dispatch. Use when the user says "log this", "track that", "note this down", or types /super-bootstrap:log — and when Claude needs to file its own findings (out-of-scope findings from a review, audit…
triage
Read-only grounding phase for a card — every card's pickup. /super-bootstrap:triage {ID} dispatches the triage subagent (Opus) to ground the card cold — premise verify, aim validate, blast collect — and append a Verdict block — ## Verdict — auto-fix · {date} (Fix-shape / Probe-deps / Execution tags) or ## Verdict …
drain
Parallel-worktree auto-drain of the board. One /super-bootstrap:drain turn = scan the pipeline sources (specs/plans/backlog, plus the scale module's test queue when present) → keep only admissible items → relation-analyze into a conflict-free wave → confirm with the user → spawn one isolated git worktree + headless…