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-new-taskgit 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-new-task)<a href="https://agentmods.dev/skills/uhappylogic/cairn/discuss-new-task"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/discuss-new-task/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-new-task"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/discuss-new-task.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 | $0.01596 |
| Opus 5 | $0.00016 | $0.00798 |
| Sonnet 5 | $0.00007 | $0.00319 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
discuss-new-task 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 3d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
discuss-new-task
Facilitates a short, focused conversation that turns a half-formed issue — the kind that surfaces mid-flight — into a description concrete enough to become a task. This skill is the conversational front-end for /submit-task: it clarifies just enough, then proposes the handoff. It never creates or edits any files, including the task list — producing the task(s) is submit-task's job.
Most issues are a single task. But some are a bigger chunk of work that only makes sense as several tasks — the user may flag this up front ("this might be a few entries"), or it may become apparent mid-discussion that one "issue" is really two or three independent pieces. When that happens, this skill helps draw the boundaries and produces an ordered set of task-sized descriptions, then hands each off in turn.
The bar to clear is conceptual clarity, not full design detail. For each task that comes out of the discussion, three things must be unambiguous:
- Which system the issue touches (a file, component, section, or requirement).
- What the desired behavior is — what should be true after the fix that isn't true now.
- Roughly how you'd verify it — what you'd look at to confirm it's done.
When the work splits into several tasks, one more thing must be clear: where the boundaries are — each piece should be independently completable, and their order (what depends on what) should be evident.
Once those are clear, submit-task takes over — keep what you produce high-level. Don't push the conversation, or the descriptions you write, past conceptual clarity.
Usage
/discuss-new-task <issue description>
<issue description>: a free-form, possibly rough description of a problem, gap, or idea surfaced mid-flight. May be a single issue or a larger "we need to create X" that spans several pieces.
Example (single task):
/discuss-new-task the setup section's steps are out of order, feels confusing
Example (likely several tasks):
/discuss-new-task I think we need a proper glossary — this is probably a few tasks, not one
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.
- 3d ago Changed 0265471630bc
- 4d ago Changed · -10 lines · -137 tokens per session f7f7a36689d6
- 9d ago First seen · 130 lines · 170 tokens per session scan A a6986d8ee2e4
discuss-new-task 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 1,596 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…