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 skills add nirecom/agents --skill issue-reconcilegit clone --depth 1 https://github.com/nirecom/agentsWrote 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/nirecom/agents/issue-reconcile)<a href="https://agentmods.dev/skills/nirecom/agents/issue-reconcile"><img src="https://agentmods.dev/badge/skills/nirecom/agents/issue-reconcile/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/skills/nirecom/agents/issue-reconcile"><img src="https://agentmods.dev/badge/skills/nirecom/agents/issue-reconcile.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 | $0.00044 | $0.00953 |
| Opus 5.5 | $0.00018 | $0.00381 |
| Sonnet 5.5 | $0.00009 | $0.00191 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
issue-reconcile 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 11d 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.
/issue-close-stage + /issue-close-finalize is the sanctioned close path
inside Claude Code, but the enforce-issue-close.js hook only covers Claude
Code's Bash tool. Issues closed elsewhere have no
<!-- issue-close-sentinel: appended --> comment
and never trigger doc-append. This skill walks closed issues, detects
missing sentinels, and backfills entries.
Usage: /issue-reconcile
Pre-flight
AGENTS_MAIN_ROOTmust be set.- Read
rules/github-issues.md— on-demand-only, never auto-injected.
IRC-1: pre-resolve
Resolve in main: <OWNER_REPO> — read it from the stdout of the standalone call gh repo view --json owner,name --jq '.owner.login + "/" + .name' — plus <HISTORY_MD_PATH> (absolute path to docs/history.md) and <HISTORY_DIR_PATH> (absolute path to docs/history/).
IRC-2: scan via worker
Dispatch the issue-reconcile worker per skills/_shared/worker-dispatch.md. Payload: owner_repo, history_md_path, history_dir_path, artifact_dir (the PLANS_DIR from WD-1), limit (omit for the 1000-issue default).
On status: failed: stop and report. A scan truncated at <N> summary means the closed-issue scan hit limit — re-dispatch with a higher limit rather than acting on the partial result. On status: complete: read the JSONL artifact — issues with classification: needs-reconcile feed IRC-3.
IRC-3: prompt and append
For each non-clean issue, show the user:
- Issue number, title, closedAt
- Classification (sentinel-only / unappended)
- The Background/Changes (or Cause/Fix) the entry would carry
Ask whether to append, skip, or stop.
On "append":
Run one standalone call per issue: bash "$AGENTS_MAIN_ROOT/skills/issue-reconcile/scripts/append-one.sh" "<NUM>". It stages the current docs/history.md, appends the entry with --allow-backdate, and PUTs the result back through the Contents API.
The script is internally idempotent — running it on history-only does
nothing harmful — but skip those in IRC-2 anyway to avoid unnecessary
GitHub API calls.
What ships with it
2 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.
- 11d ago Changed eee016e750d4
- 21d ago Changed 05eb6ced4b0f
- 1mo ago Changed · -18 lines 74e3e8d8b3cf
- 1mo ago First seen · 98 lines · 44 tokens per session scan A a8bb0fa236e8
issue-reconcile is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 953 once invoked, about $0.0002 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 skills, from other repositories
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…
cuga-github-issues
Create GitHub issues for cuga-agent (bugs, features, epics, designs, and related work) against origin using gh, with epic → feature → issue hierarchy and GraphQL sub-issue linking. Use when the user says create new issues, report a bug, file a bug, feature request, new feature, create an epic, GitHub issue, sub-issue…