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 agentmods add skills/uhappylogic/cairn/submit-tasknpx skills add uHappyLogic/cairn --skill submit-taskgit clone --depth 1 https://github.com/uHappyLogic/cairnWhat 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 | $0.00073 | $0.01236 |
| Opus 5 | $0.00036 | $0.00618 |
| Sonnet 5 | $0.00015 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
submit-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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
submit-task
Turns a single, already-clear issue into a fully-specified task in the current
milestone's TASKS_TODO.md. This skill is the user-facing entry point
(/submit-task) and the handoff target for /discuss-new-task.
It does two things the agent can't: the triage and positioning that need the whole
task list in view — checking for duplicates and deciding where the task belongs — and then
it authors and inserts the task inline, in this conversation. Running the authoring
inline is deliberate: the contract surface, notes, and success criteria you just wrote stay
in context, so the user can immediately ask why a choice was made or request a tweak. For
bulk authoring, derive-tasks instead spawns the submit-task agent, which
runs the same shared procedure in isolation so N tasks' reasoning never lands in its
context. If the issue is still vague or might be several tasks, use
/discuss-new-task first.
Invocation
/submit-task <issue description>
<issue description> is a free-form description of a problem or gap discovered during
development, specific enough that the affected system, desired behavior, and how to verify
it are clear.
Workflow
0. Find the current milestone
Follow ${CLAUDE_PLUGIN_ROOT}/shared/get-current-milestone.md to resolve <MILESTONE_DIR>. Never use a hardcoded task-list path.
1. Read context for triage
Read in parallel:
<MILESTONE_DIR>/requirements.md— to confirm the issue fits the milestone's scope.<MILESTONE_DIR>/TASKS_TODO.md— existing pending tasks, for duplicate-detection and positioning.<MILESTONE_DIR>/TASKS_DONE.md— completed work, to catch issues already addressed.
2. Triage
- Duplicate? If an existing pending task or a completed task already covers this issue, stop and tell the user which task covers it. Do not add a duplicate.
- In scope? If the issue clearly belongs to a different milestone or is really an open design decision, say so and point to the better tool (
/discuss-open-question) instead of queuing it.
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 First seen · 104 lines · 73 tokens per session scan A 59f840254d0e
submit-task is a skill published in the GitHub repository uHappyLogic/cairn (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,236 once invoked, about $0.0004 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
zh-output-example
Reviews Chinese skill documentation for publication readiness. Invoke when the user asks in Chinese to review a skill.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
company-hiring-intelligence
Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…
文档协作
引导用户通过结构化的文档共同编写工作流程。当用户想撰写文档、提案、技术规范、决策文档或类似结构化内容时使用。该工作流程帮助用户高效传递上下文，通过迭代优化内容，并验证文档对读者有效。当用户提到写文档、创建提案、起草规范或类似文档任务时触发。.
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.