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/stefan-jansen/coding-agent-toolkit/plan-issuesnpx skills add stefan-jansen/coding-agent-toolkit --skill plan-issuesgit clone --depth 1 https://github.com/stefan-jansen/coding-agent-toolkitWhat 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 | $0.00096 | $0.01992 |
| Opus 5 | $0.00048 | $0.00996 |
| Sonnet 5 | $0.00019 | $0.00398 |
| Haiku 4.5 | $0.00010 | $0.00199 |
Grade A, and why
plan-issues 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-issues — project the plan onto GitHub
You are running the PLAN-ISSUES step of the workflow. Your job is to
turn the durable plan.md (produced by the headless plan step) into a GitHub
milestone + one issue per planned issue, so that subsequent /next work
units can be traced 1:1 to a closed issue.
This step is host-neutral: same contract on Claude and Codex. The verb is
gh. The agent (you) parses the markdown and shells gh.
Arguments
Parse these from the user's invocation (any order):
| Arg | Required | Default | Meaning |
|---|---|---|---|
--repo <owner/name> |
yes | — | Target GitHub repo |
--plan <path> |
no | active work unit's plan.md |
Plan file to parse |
--milestone <title> |
no | the milestone heading in plan.md |
Override the milestone title |
--apply |
no | false (dry-run) | Actually create. Without it, only print what would happen |
--branch <name> |
no | none | If set, ensure the branch exists locally before opening issues (so gh issue develop is wired). Optional. |
If --plan is omitted, locate the active work unit:
- Look at the user's current working directory and walk up to a
.workspace/work/dir. - Inside it, the active unit is the most recently modified subdirectory that contains a
plan.md. - If ambiguous, ask the user which work unit, and offer the candidates.
If --repo is omitted, stop and ask. Never guess the repo.
What "Issue N" looks like in plan.md
The convention (see align's sibling plan step) produces headings of
the form:
### Milestone: `<version> — <title>`
**Issue 1 — <issue title>**
<one or more paragraphs of body — files, tests, acceptance>
**Issue 2 — <issue title>**
<body>
Parsing rules:
- The milestone is the first
### Milestone: \X — Y`line. The full backticked string (X — Y`) is the milestone title. - An issue heading matches
^\*\*Issue\s+(\d+)\s+—\s+(.+?)\*\*\s*$— capture the number and the title. (Both em-dash and ASCII--accepted.) - An issue's body is every line after its heading up to (but not
including) the next
**Issue N —, the next top-level heading##, or EOF. Trim leading/trailing blank lines.
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 · 214 lines · 96 tokens per session scan A 8affd4a71188
plan-issues is a skill published in the GitHub repository stefan-jansen/coding-agent-toolkit (22 stars, last pushed 16d ago), licensed MIT. It adds 96 tokens to every session and 1,992 once invoked, about $0.0005 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
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…
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.
github-workflow
Use GitHub workflow tools to read work status, draft reports, summarize follow-ups, and execute only approved issue mutations.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
dot-ai-prd-create
Create documentation-first PRDs that guide development through user-facing content.