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 paultyng/skill-issue --skill implement-plangit clone --depth 1 https://github.com/paultyng/skill-issueWrote 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/paultyng/skill-issue/implement-plan)<a href="https://agentmods.dev/skills/paultyng/skill-issue/implement-plan"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/implement-plan/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/paultyng/skill-issue/implement-plan"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/implement-plan.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 | $0.00200 | $0.03581 |
| Opus 5.5 | $0.00080 | $0.01432 |
| Sonnet 5.5 | $0.00040 | $0.00716 |
| Haiku 4.5 | $0.00020 | $0.00358 |
Grade B, and why
implement-plan scanned grade B 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Implementer must probe before claiming DONE — run the verification command, grep for the expected change, do not paraphrase "should work" as evidence. Per `~/.claude/rules/probe-not-assume.md`. How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Plan
Drive an approved implementation plan to completion: review-plan gate → per-task loop (implementer → verify → reviewer → triage → commit → tick) → end-of-plan review. Manual invocation only. Never auto-creates PRs.
Workflow
1. Resolve the plan and check preconditions
Plan resolution (priority order):
- Explicit path argument (e.g.
/implement-plan .plans/auth-rewrite.md). ./.plans/PLAN.mdin cwd.- Latest by mtime in
./.plans/*.md. - Legacy fallback (one-release transition):
./PLAN.mdin cwd, then latest by mtime in./docs/plans/*.md. If either resolves, warn once:Plan resolved from legacy path <X>; consider moving under .plans/. - None resolve → stop, ask the user. Do not guess. Do not assume "do it" meant something else; if no plan, this skill should not have activated — exit cleanly.
CLAUDE.md override: if the project CLAUDE.md (or CLAUDE.local.md) contains a directive like Plans live in <path>, use <path> as the primary discovery dir instead of .plans/. Skip the gitignore bootstrap below in that case — the user has taken responsibility for the path.
After resolving a path under .plans/ (steps 2 or 3), call once per run:
~/.claude/scripts/ensure-gitignore.sh '.plans/'
This is idempotent. Skip for legacy paths (step 4) and for CLAUDE.md overrides.
Read the plan file fully. Capture: total task count, unchecked task count, any Branch policy section (see reference.md → Plan header conventions), and any Behavior delta section (its Acceptance: criteria are verified at end-of-plan, step 5).
Precondition checks (fail-fast — abort with a clear message if any fails):
# In a git repo?
git rev-parse --is-inside-work-tree >/dev/null 2>&1 || abort "not a git repo"
# Working tree clean? Catches uncommitted + untracked (.plans/ is gitignored, so plan files are invisible to git — that is intentional).
[ -z "$(git status --porcelain)" ] || abort "working tree not clean — commit, stash, or discard first"
# origin remote exists?
git remote get-url origin >/dev/null 2>&1 || abort "no 'origin' remote — see reference.md for fallback"
What ships with it
1 file 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.
- 5d ago Changed · +2 lines b37cf0a7ee2f
- 1mo ago First seen · 231 lines · 200 tokens per session scan B 8d5be999cd8e
implement-plan is a skill published in the GitHub repository paultyng/skill-issue (8 stars, last pushed 2d ago), licensed MIT. It adds 200 tokens to every session and 3,581 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
confluence-assistant
Central hub for Confluence operations - routes requests to specialized skills. ALWAYS use when user mentions confluence, wiki, or Atlassian wiki operations.
confluence-bulk
Bulk operations for 50+ pages - updates, moves, deletions, labels, and permissions. Use when updating multiple pages simultaneously (dry-run preview included), needing rollback safety, or coordinating team changes. Handles partial failures gracefully.
confluence-template
Work with page templates and blueprints. ALWAYS use when user wants to create standardized pages or manage templates.
confluence-admin
Confluence administration including users, groups, space settings, and permission diagnostics. Use when managing user access, group membership, viewing space configuration, or checking permissions.
confluence-jira
JIRA integration - embed issues, create links between products. ALWAYS use when user wants to connect Confluence and JIRA.
workflow-client-bootstrap
WHAT — Interactive interview to capture client delivery context and store it inside the user's /.ai-workspace (or similar) as packs + knowledge (no client skills). Use when onboarding a new client project or updating an existing workspace context.