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/mimfort/rag_for_git/finish-tasknpx skills add mimfort/rag_for_git --skill finish-taskgit clone --depth 1 https://github.com/mimfort/rag_for_gitWrote 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/mimfort/rag_for_git/finish-task)<a href="https://agentmods.dev/skills/mimfort/rag_for_git/finish-task"><img src="https://agentmods.dev/badge/skills/mimfort/rag_for_git/finish-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 | $0.00043 | $0.00650 |
| Opus 5 | $0.00022 | $0.00325 |
| Sonnet 5 | $0.00009 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
finish-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 4d 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.
What it actually says
Finish Task
Reply in Russian. The server appends the PR link idempotently, completes the selected generic target, and adds a clickable task link to the PR body; clients never send credentials.
- Config. Read
task_boardfrom.review.yml, otherwiseget_board_config(). Use onlytype,project,create_target,done_target, andoptions. If no board is resolved, report a board-less no-op. - Resolve key and PR. Match
key_patternon the current branch, newestbriefsfile, orgh pr view --json title,body; otherwise ask. Resolve the PR URL withgh pr view --json url -q .url(or ask). Missing key or URL is a no-op. - Discover. Call
get_board_targets(board_type=<type>, project=<project>, provider_options=<task_board.options or {}>). Selectdone_targetfromtargetswith a done purpose. For each option withrequired_forcontainingfinish, resolve its value fromchoices; if required metadata is missing, ask instead of guessing. - Offer + confirm. Show the PR link and the resolved done target by its label plus every selected option, and state that a task link will be prepended to the PR body. Ask whether to add an optional note. Write only after explicit confirmation; never write to the board silently.
- Write. Call
Onfinish_task(key=<key>, pr_url=<url>, note=<note or null>, board_type=<type>, target=<done_target or null>, provider_options=<task_board.options or {}>)status == "error", report the reason in Russian and stop. - Re-index. Call
sync_board(board=<project or null>, board_type=<type>, provider_options=<task_board.options or {}>), then report the write and sync result. Whenalready_closedis true, state that no duplicate PR link was added. Report the task link fromtask_link_status, not fromtask_link_addedalone:added— the link was written now;already_present— it was already in the PR body, so report it as normal (an idempotent no-op, never as a problem);failed— only then relay the warning verbatim, and the board write still succeeded.task_link_addedstaystrueonly foradded(older deploys may omittask_link_status: treat a missing field asadded/failedby whether warnings mention the link).
All reads are fail-open; the explicitly confirmed finish_task call is the only write.
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.
- 4d ago First seen · 40 lines · 43 tokens per session scan A fe3b53a132af
finish-task is a skill published in the GitHub repository mimfort/rag_for_git (21 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 650 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
graft
This repo is indexed by graft/. For ANY task here, whether understanding how something works, finding where code lives, tracing what calls a symbol or what a change breaks, or scoping an edit, get your context from graft before grepping or reading source files.
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
code-graph
This skill should be used when understanding code structure, finding dependencies between functions/classes, tracing call graphs, or exploring code relationships. Trigger phrases include 'code graph', 'call graph', 'who calls', 'what calls', 'find dependencies', 'code structure', 'inheritance', 'find paths'.
codebase-exploration
Explore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts. Use when exploring code, understanding architecture, finding functions/types, analysing dependencies, searching database schemas or API specs, or when socraticode/codebasesearch tools are available. Activates…
codebase-management
Set up, index, and manage SocratiCode codebase indexing. Use when the user wants to index a project, check infrastructure health, start/stop file watching, configure context artifacts, troubleshoot indexing issues, manage the code graph, or any SocratiCode administrative task. Activates when the user mentions…
agentmap
Use for TypeScript/JavaScript codebase navigation — symbol lookup, blast radius, reuse checks, and repo orientation. Prefer agentmap before serial grep when exploring imports, exports, or where a symbol lives. Package is @raymondchins/agentmap (not the unrelated npm package agentmap).