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 discuss-milestone-goalgit 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/discuss-milestone-goal)<a href="https://agentmods.dev/skills/uhappylogic/cairn/discuss-milestone-goal"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/discuss-milestone-goal/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/discuss-milestone-goal"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/discuss-milestone-goal.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 | $0.00033 | $0.00619 |
| Opus 5 | $0.00016 | $0.00309 |
| Sonnet 5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
discuss-milestone-goal 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 6d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
discuss-milestone-goal
Facilitates a structured conversation to sharpen a vague or incomplete milestone goal into a clear, actionable statement ready for /define-milestone-goal. The output is a refined goal description — not a document yet: this skill is purely conversational, creates no files, and assigns no milestone number (that is the user's decision).
Usage
/discuss-milestone-goal <overall_goal_description>
<overall_goal_description>: a free-form description of what you want the milestone to accomplish.
Example:
/discuss-milestone-goal add a getting-started guide that walks a new user through their first session
Workflow
1. Read project context
Read CLAUDE.md to understand the current milestone, the project's domain context, and project overview. Read milestones/README.md to understand what has already been built in past milestones. This grounds all questions in the real project state.
2. Analyze the goal
Identify what is clear, what is ambiguous, and what is missing. Look for:
- Scope ambiguity — what exactly is in vs. out?
- Dependency gaps — does this assume systems that don't exist yet?
- Success criteria — how would you know the milestone is done?
- Conflicts — does anything in the goal conflict with the current architecture or existing milestones?
3. Open with a crisp framing
Restate the goal in one sentence to show you understood it. Then immediately surface the most important ambiguities as direct questions. Do not pad with preamble or list every possible concern — focus on the two or three questions whose answers would most change the scope.
Format as:
Understood goal: one sentence.
Questions:
- ...
- ...
- (optional) ...
4. Continue the conversation
After each user answer, either:
- Ask the next most important clarifying question, or
- Confirm that the goal is now clear enough to define
Ask questions one at a time when the user seems overwhelmed; batch them when context is thin and answers are likely short. Keep each response short after the opening — the conversation should move fast. Do not ask questions for their own sake. Stop when the goal is specific enough that /define-milestone-goal could fill requirements.md without further guessing.
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.
- 6d ago Changed · -8 lines e4d38399926e
- 11d ago First seen · 75 lines · 33 tokens per session scan A 8388ef556e38
discuss-milestone-goal is a skill published in the GitHub repository uHappyLogic/cairn (2 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 619 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-init
Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…
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…
debt-ops-metrics
Print a debt-ops health summary from the metrics log, covering registration rate, feedback action rate, ADR creation, and AI-authored share. Use when the user asks for "debt-ops metrics", "debt health", "registry stats", or a tech-debt health summary. Read-only, never writes the log.
review
Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.
plan-task
Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.
scout-consolidation
Launch a Scout consolidation session as a background process. Runs a lighter delta scan — captures what changed since the last run and updates action items and KB.