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/nirecom/agents/issue-close-finalizenpx skills add nirecom/agents --skill issue-close-finalizegit clone --depth 1 https://github.com/nirecom/agentsWhat 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 | $0.00074 | $0.02940 |
| Opus 5 | $0.00037 | $0.01470 |
| Sonnet 5 | $0.00015 | $0.00588 |
| Haiku 4.5 | $0.00007 | $0.00294 |
Grade A, and why
issue-close-finalize 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage routes to the correct subset of steps; each step is idempotent and resumable. Read rules/github-issues.md first — on-demand-only, never auto-injected; its "Session model" defines per-session N. Usage: /issue-close-finalize <N> or /issue-close-finalize --from-session.
Read rules/coding.md before the first close comment or parent-body update — on-demand-only, never auto-injected; its Public GitHub Rules govern that outbound text.
--from-session resolves <N> from ${WORKFLOW_PLANS_DIR:-$HOME/.workflow-plans}/<session-id>-intent.md ## Issues (canonical parser: hooks/lib/parse-closes-issues.js). Zero → skip; one → continue; multiple → run sequentially; missing intent → one-line warn + skip. The merge commit is resolved from the PR in Step ICF-B, not from a flag.
--from-session per-N dispatch obligations
Enumerate every N in closes_issues via parse-closes-issues.js — the ## Issues block lists all values, including subsumed siblings. For each N in insertion order:
- Open sub-issue gate (#417): before dispatching the pipeline, if the issue is OPEN, run
bash "$AGENTS_CONFIG_DIR/bin/github-issues/parent-all-closed-check.sh" "$OWNER_REPO" <N>. On exit 1 (open sub-issues): emitWarning: issue #<N> has open sub-issues — skipping close pipeline. Close sub-issues first., write askipped_open_sub_issuesoutcome entry viabin/issue-close-write-outcome.js, and skip the pipeline for this N. - All-N outcome entries (#695): after the pipeline completes or is skipped, ensure EVERY enumerated N has an outcome entry — including subsumed siblings that never ran a pipeline. Write missing entries with the appropriate skip state before the End report.
- Early-return outcome entries (#827): at any early-return path —
meta_pending_subsearly return, or a terminal-phase early return when triage reports the issue is already in its terminal state — write an outcome entry for that N before returning (states:skipped_meta_pending_subs,already_closed,skipped_open_sub_issues, as fits the branch).
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 101 lines · 74 tokens per session scan A 0c3ee487f6d3
issue-close-finalize is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 2,940 once invoked, about $0.0004 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
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
dot-ai-prd-create
Create documentation-first PRDs that guide development through user-facing content.
agent-upkeep
Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or unattended upkeep runs that improve unit test coverage for one file, fix one behavioral bug in one module, or move one off ESLint rule toward enforcement to reduce…
bmad-check-implementation-readiness
Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".