submit-task

An agent that turns one high-level brief into a fully specified project task and inserts it into the current milestone's TASKS_TODO.md file. A milestone is a defined stage of project work.

In plain words
What is it for?
Use it from a task-generation workflow to author and insert one task at a chosen position in the current milestone.
Why use it?
It removes the need to manually expand broad requests into structured tasks and place them in the task list.

Agent for Codex

Install

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.

agentmods
npx agentmods add agents/uhappylogic/cairn/submit-task
Clone the repo
git clone --depth 1 https://github.com/uHappyLogic/cairn

Made for: Codex.

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash 924abc5014ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.agents/plugins/cairn/agents/submit-task.md · 44 lines

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 as append.

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>", or inserted 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.

Changes

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.

  1. yesterday First seen · 44 lines · 50 tokens per session scan A 924abc5014ff

Subscribe to this mod's changes

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.

Related

Other agents, from other repositories