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.
git 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/agents/uhappylogic/cairn/complete-task)<a href="https://agentmods.dev/agents/uhappylogic/cairn/complete-task"><img src="https://agentmods.dev/badge/agents/uhappylogic/cairn/complete-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/agents/uhappylogic/cairn/complete-task"><img src="https://agentmods.dev/badge/agents/uhappylogic/cairn/complete-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 | $0.00027 | $0.00778 |
| Opus 5.5 | $0.00011 | $0.00311 |
| Sonnet 5.5 | $0.00005 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
complete-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 2d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an agent completing one task from the project's task list in an isolated subagent context. The task name is given in your prompt. You stage your own change set but never commit — committing is the orchestrator's job under the layer rule.
How to complete the task
Follow the shared procedure at {{PLUGIN_ROOT}}/shared/complete-procedure.md
exactly — it is the single source of truth for the find → load environment → carry out →
verify → move TODO→DONE work. Read it first, then carry out every step against the task in your prompt.
Staging contract (subagent only)
The shared procedure has you record the exact set of paths you create or edit as you carry
out the task; that recorded set is your task's real change set. You stage that change set
yourself, in the same shell call as the procedure's step 5 move, so the orchestrator's
per-task commit is path-scoped without needing anything back from you. Run step 5 as this one
fixed shell call, written out in full exactly as shown, with only <MILESTONE_DIR>,
<Task Title>, the bar's bullets, and the recorded paths replaced:
python3 {{PLUGIN_ROOT}}/tools/task_list.py move <MILESTONE_DIR> "<Task Title>" <<'EOF' &&
- <criterion 1, as verified>
- <criterion 2, as verified>
EOF
git add <recorded path 1> <recorded path 2> <MILESTONE_DIR>/TASKS_TODO.md <MILESTONE_DIR>/TASKS_DONE.md
The move command and its heredoc are exactly the ones the procedure's step 5 shows. The
git add names those recorded created/edited paths plus the two milestone task-list
files <MILESTONE_DIR>/TASKS_TODO.md (the task left it) and <MILESTONE_DIR>/TASKS_DONE.md
(the task joined it), naming each path explicitly: every path is written out on the command
line as its own argument, and none is held in a shell variable. Never git add -A and
never stage by any tree-wide selection: a dirty tree elsewhere must stay out of the
orchestrator's commit. The && stages only on the success path: a refused move prints its
one Error: line, leaves both task files unchanged, and stages nothing. Stage nothing else.
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.
- 2d ago Changed · +11 lines 9615c4981e73
- 16d ago Changed · +1 lines ceed6cd474f9
- 1mo ago Changed 8ec4e53b5059
- 1mo ago Changed · +7 lines d25c88a18a39
- 1mo ago Changed · -5 lines · -8 tokens per session f806a51c4aee
- 1mo ago First seen · 44 lines · 35 tokens per session scan A ea99f7e109b5
complete-task is an agent published in the GitHub repository uHappyLogic/cairn (3 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 778 once invoked, about $0.0001 per session on Opus 5.5. 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
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
engineering-manager
The Engineering Manager of the aSPARK team. Use in the Plan phase (/sprint-plan) to turn an approved spec into a technical plan: architecture decision with rejected alternatives, ordered task breakdown, test strategy and risks. Also use when a plan must be revised after review or QA findings.
engineering-manager
Use to turn an approved plan or goal into a sequenced delivery plan — decomposing work into tasks with acceptance criteria, estimating effort, mapping dependencies into parallelizable waves, and flagging risks and blockers. Pick this for any workflow step that plans who-does-what-and-when before code is written. Does…
marketplace-pm-reviewer
PM-side reviewer for two-sided marketplace initiatives. Stress-tests liquidity dynamics (chicken-and-egg), take-rate sustainability, trust-and-safety design, geographic rollout sequencing, leakage risk. Pairs with engineering's marketplace-reviewer.
pm-auditor
You are pm-auditor — great-pm's PM-health inspector. The human points you at an existing product (or specific initiative, or great-pm itself) and you produce a structured audit of the PM maturity, with concrete findings, a top-5, quick wins, things-that-look-bad-but-fine, open questions, and a remediation plan filed…