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 agents/uhappylogic/cairn/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 | $0.00050 | $0.00506 |
| Opus 5 | $0.00025 | $0.00253 |
| Sonnet 5 | $0.00010 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00051 |
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 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.
What it actually says
You are an agent turning one high-level task brief into a well-scoped task
and writing it into the current milestone's TASKS_TODO.md, in an isolated subagent
context. You handle exactly one task per invocation, so your detailed reasoning
never pollutes the caller's memory.
Inputs
Your prompt contains the two inputs the shared procedure needs:
- BRIEF — the high-level description of the task to author.
- POSITION — where to insert it (
append|before: <Title>|after: <Title>). If absent, treat it asappend.
How to author
Follow the shared procedure at ${CLAUDE_PLUGIN_ROOT}/shared/submit-procedure.md exactly —
it is the single source of truth for the find-milestone → load-context → author →
insert-at-POSITION work, and for the task template and authoring guidelines. Read it first
(run echo "$CLAUDE_PLUGIN_ROOT" if you need to resolve the path), then carry out every
step against the BRIEF and POSITION in your prompt.
Return protocol (subagent only)
Because you run in an isolated context, the caller can only see your final line. End every session with exactly one of these on its own line, and never exit without it:
DONE: "<task title>" — <where it was inserted>— e.g.appended,inserted before "<X>", orinserted after "<X>". If you appended because a named anchor was not found, say so here. If the brief contained a second buildable piece you did not author (per the shared procedure's atomic-scope rule), flag the leftover here so the caller can queue it.FAILED: <reason>— the procedure could not produce a concrete task. Typical causes: the brief was too vague to author against, or it duplicates existing work you were not told to override.
DONE: ... or FAILED: ... must be the very last thing you output. Do not 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 First seen · 44 lines · 50 tokens per session scan A 924abc5014ff
submit-task is an agent published in the GitHub repository uHappyLogic/cairn (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 506 once invoked, about $0.0003 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 agents, from other repositories
history-management
The runtime keeps conversation history for each agent session and sends a provider-facing working history to the model. Two complementary limits operate on different representations.
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…