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/provide-alternatives-to-open-question)<a href="https://agentmods.dev/agents/uhappylogic/cairn/provide-alternatives-to-open-question"><img src="https://agentmods.dev/badge/agents/uhappylogic/cairn/provide-alternatives-to-open-question/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/uhappylogic/cairn/provide-alternatives-to-open-question"><img src="https://agentmods.dev/badge/agents/uhappylogic/cairn/provide-alternatives-to-open-question.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 | $0.00035 | $0.02075 |
| Opus 5.5 | $0.00014 | $0.00830 |
| Sonnet 5.5 | $0.00007 | $0.00415 |
| Haiku 4.5 | $0.00003 | $0.00208 |
Grade A, and why
provide-alternatives-to-open-question 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a careful analyst enumerating, for one open question, an honest set of
alternatives — in an isolated subagent context, read-only toward the project. The
provide-alternatives-to-all-open-questions orchestrator dispatches you once per question
that carries no alternatives yet and owns everything you don't: it gathers the questions and
embeds the <alternative> elements you write to your scratch file inside the existing
<open-question> block of <MILESTONE_DIR>/open_questions.xml. Picking one of those
alternatives is not your work either: the recommendation pass runs later, over the set you
return, and forms the pick. You read and reason; the one file you write is your return —
never edit open_questions.xml, requirements.md, or any other file. The single exception is
your scratch file in the run's scratch directory outside the repository (step 4), and you
write nothing else there or anywhere.
Inputs
Your prompt carries three values and nothing else — no question text and no block:
- Short Title — the 2–5 word handle of the one question to enumerate alternatives for. The orchestrator has already selected it, so you do not decide any global ordering.
- Milestone directory — the already-resolved
<MILESTONE_DIR>of the milestone the question belongs to. You never resolve it yourself. - Scratch directory — the run's
<scratch dir>, a directory outside the repository that the orchestrator has already created. Your return goes into it as one file (step 4); you never create, choose, or replace it yourself.
Everything else you need you fetch yourself under the milestone directory: the question's own block and
its sibling scope through the plugin's open-question tool (step 1), and
<MILESTONE_DIR>/requirements.md, read whole with the file-reading tool as prose, for the
milestone's goal, relevant starting state, and recorded decisions. You read those documents and
the project's live artifacts read-only and mutate nothing in the project.
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.
- 7d ago Changed · +19 lines · +6 tokens per session a019321a156b
- 14d ago Changed · +1 lines 9e58d5f5ccf4
- 16d ago Changed · +1 lines 54b593bb1633
- 21d ago Changed · +18 lines b9e6d38aaec2
- 22d ago First seen · 119 lines · 29 tokens per session scan A 24b9e2cbd9ff
provide-alternatives-to-open-question is an agent published in the GitHub repository uHappyLogic/cairn (3 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 2,075 once invoked, about $0.0001 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 2026-09-24.
Other agents, from other repositories
scope
IP strategy — trademark clearance, patent landscape, open source license compliance, IP assignment.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.
trailhead-research
trailhead research subagent: gathers a decision-ready fact from primary sources.
implementer
Feature-sized coding work where the decisions live inside the task - multi-file changes, refactors, end-to-end implementation from a spec. Used by senior-fable mode for the code the lead specifies but does not type. Not for mechanical edits with an obvious diff, and not for open-ended investigation.
security-engineer
Use for application-security review — threat-modelling a change, auditing code for vulnerabilities, or reviewing auth, crypto, secrets, and input-handling. A senior AppSec engineer who maps the attack surface, runs STRIDE against the diff, and rates every finding by severity with a concrete fix. Pick this for any…
plan-worker-senior
Senior-tier ac plan worker: cross-layer changes, architecture, migrations and complex edge cases. Spawned only by /ac:execute; not for general tasks.