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 cboone/agent-harness-plugins --skill address-issuegit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/address-issue)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/address-issue"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/address-issue/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/cboone/agent-harness-plugins/address-issue"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/address-issue.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 | $0.00049 | $0.03044 |
| Opus 5.5 | $0.00020 | $0.01218 |
| Sonnet 5.5 | $0.00010 | $0.00609 |
| Haiku 4.5 | $0.00005 | $0.00304 |
Grade C, and why
address-issue scanned grade C with 1 finding 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 15d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- prettier-ignore --> How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address Issue
Fetch a GitHub issue, plan the work, stop for approval, then execute changes and commit with issue references.
Options
The user may provide these options inline:
- --dry-run: Fetch and analyze the issue, present the plan, but do not change files or GitHub state, including assignments and labels
- --no-approval: Skip the approval stop in step 6 and go straight from the plan to execution
- --no-commit: Make changes but do not commit them
- --commit-per-change: Commit after each logical change instead of grouping at the end
--dry-run and --no-approval are opposite ends of the same gate: --dry-run stops permanently after the plan, the default stops and resumes once the user approves, and --no-approval never stops.
Several Issues
Several issue numbers, as in /address-issue 42 57, share one plan and one approval gate. Step 6 may propose separate PRs and must identify which changes belong on the current branch. workmux:start-issue chains into this form when it opens one worktree for several issues. Every step below applies to each issue, as follows:
- Step 1: fetch every issue by number. Several issues are always given as numbers; descriptive text names one issue and follows the single-issue workflow.
- Step 2: check each issue's state. Ask about every closed issue at once, and drop any the user declines.
- Step 3: unless
--dry-runwas specified, self-assign and label each open issue, recording the result for each one. - Step 4: show every issue's context, one block per issue.
- Step 5: classify each issue and extract its sub-tasks, keeping track of which issue each sub-task came from.
- Step 6: collect every issue's requirements into one plan, headed
## Plan for Issues #42, #57, that says which change serves which issue. There is one approval gate for the whole plan, not one per issue. - Step 8: each commit references every issue its change addresses, as in
feat: add dark mode toggle (#42, #57), and together the commits reference every issue addressed on the current branch. The commit prefix follows the classification of the issue or issues the commit addresses. - Steps 9 to 11: report the status of every issue, including which are marked in progress and which sub-tasks remain for each.
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.
- 15d ago Changed · +4 lines · -1 tokens per session 6fdd181a78b2
- 16d ago Changed 05147f916766
- 20d ago Changed · +16 lines · +14 tokens per session fb046d565ecb
- 26d ago Changed · +1 lines 4d3162893f5e
- 1mo ago Changed · -5 lines · -79 tokens per session 20099067862b
- 1mo ago Changed · +19 lines · +6 tokens per session 12e6009e14f0
- 1mo ago First seen · 218 lines · 109 tokens per session scan C 86a6a49725a2
address-issue is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 3,044 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). 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.
gait-session-tracking
GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.
autopilot-triage
Vet open issues for autonomous resolution and queue the qualifying ones with the autopilot-queued label — the start-of-day "fill the queue" half of the triage → run split.
effect-ledger
Record an effect, sign an effect, reconcile an effect or check "did this PR merge" through the signed AIWG effect ledger, using one aiwg effect command with scriptable exit codes.
omh-ralph-task
Execute one omh-ralph task: file-scope, commit, report.
phel-gh-issues
The gh-issues skill reads this file. It holds only what this repository adds to the generic queue workflow (clean tree, queue of issues unassigned or assigned to me, oldest first, one at a time). Where they differ, this file wins.