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/complete-tasknpx skills add uHappyLogic/cairn --skill complete-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/complete-task)<a href="https://agentmods.dev/skills/uhappylogic/cairn/complete-task"><img src="https://agentmods.dev/badge/skills/uhappylogic/cairn/complete-task.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00849 |
| Opus 5 | $0.00025 | $0.00425 |
| Sonnet 5 | $0.00010 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
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 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
complete-task
Completes one named ad-hoc task inline, in the current conversation — not in a subagent. Running inline is the whole point: the work reasoning (which files changed, why, and what the verification showed) stays in context, so you can follow up right after — ask why a choice was made, request a tweak, or extend the work — without the context being thrown away.
For completing the whole task list unattended, use /complete-all-tasks instead — that
orchestrator deliberately runs each task in an isolated subagent and commits after each.
Invocation
/complete-task <task name>
<task name> is the full or partial text of a ## heading in the current milestone's
TASKS_TODO.md. The procedure resolves the current milestone itself (from CLAUDE.md), so
nothing needs to be looked up first.
Workflow
1. Run the shared procedure inline
Read and follow the shared procedure at
${CLAUDE_PLUGIN_ROOT}/shared/complete-procedure.md (run echo "$CLAUDE_PLUGIN_ROOT" if
you need to resolve the path), carrying out every step yourself, in this conversation.
Do not spawn the complete-task agent — that would discard the working context
this skill exists to keep.
If no task matches the given name, the procedure has you stop without changes; tell the user
that and list the available ## headings so they can retry with a correct name.
2. Commit the completion
When the procedure finishes (success criteria verified, task moved to TASKS_DONE.md),
read and follow the shared commit procedure at
${CLAUDE_PLUGIN_ROOT}/shared/commit-procedure.md (run echo "$CLAUDE_PLUGIN_ROOT" if you
need to resolve the path), carrying out its steps yourself. Supply it these two inputs:
- PATHS — this skill's own change set: the exact paths the shared completion procedure
recorded as it created or edited files while carrying out the task, 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). Name each path explicitly — nevergit add -A. - SUBJECT —
Task-completion: <task heading>.
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 · 80 lines · 50 tokens per session scan A d585ee90fc41
complete-task is a skill published in the GitHub repository uHappyLogic/cairn (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 849 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 skills, from other repositories
setup
This skill should be used when "milestone-driver:setup" is invoked directly, OR auto-invoked by solve-issue/solve-milestone when the driver profile is absent or missing a required Core key (integrationBranch, protectedBranch, or sourceGlobs). Guides an interactive first-run bootstrap that infers every profile key from…
smcp-handoff
Resume prior work from a saved subagent-mcp handoff when the user says "handoff-resume", "resume handoff", or "resume work"; call handoff-read, then confirm intent with exactly 4 structured questions before acting, and know the handoff-write/read/clear lifecycle.
solve-issue
This skill should be used when the user invokes "/milestone-driver:solve-issue ", or asks to "solve issue ", "fix issue ", or "drive issue " through the milestone-driver gated procedure. Runs one GitHub issue end-to-end as an orchestrator - triage, root-cause-or-park, dispatch the implementer subagent (TDD…
solve-milestone
This skill should be used when the user invokes "/milestone-driver:solve-milestone ", or asks to "solve a milestone", "drive a milestone", or "work the milestone autonomously". Iterates every issue in a GitHub milestone in dependency order via /milestone-driver:solve-issue, re-syncing the integration branch between…
wf-pm
Sole team lead of the waterfall workflow — creates the team, dispatches OR's spawnrequest, relays HO decisions via AskUserQuestion, and runs the final git commit at CLOSURE.
wf-pm-light
PM solo pour le mode subagent-light — élicitation, specs.md, checkpoint specs, spawn TL passe 1+2, checkpoint tasks, validation finale, git commit.