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/paultyng/skill-issue/implement-plannpx skills add paultyng/skill-issue --skill implement-plangit clone --depth 1 https://github.com/paultyng/skill-issueWhat 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 | $0.00200 | $0.03501 |
| Opus 5 | $0.00100 | $0.01750 |
| Sonnet 5 | $0.00040 | $0.00700 |
| Haiku 4.5 | $0.00020 | $0.00350 |
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 3d 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 — 231 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.
- 3d 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 (9 stars, last pushed 22d ago), licensed MIT. It adds 200 tokens to every session and 3,501 once invoked, about $0.0010 per session on Opus 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
promptscript
PromptScript language expert for reading, writing, modifying, and troubleshooting .prs files. Use when working with PromptScript syntax, creating or editing .prs files, adding blocks like @identity, @standards, @restrictions, @shortcuts, @skills, or @agents, configuring promptscript.yaml, resolving compilation errors…
thesis-control
Use when AI-assisted thesis edits risk claim drift, scope creep, loss of author control, or repeated revisions that fail to converge; provides spine cards, edit contracts, drift audits, revision escalation, and human gates.
helius-jupiter
Skill "helius-jupiter" from helius-labs/core-ai, covering helius x jupiter — build defi apps on solana, mcp router surface, prerequisites, 1. helius mcp server and 2. jupiter api key.
argument-governance
Build and audit the manuscript argument system: intent, gap-contribution alignment, hierarchical claims, evidence balance, limitations, and reviewer attack surfaces. Use when a paper, thesis chapter, review article, or rebuttal needs explicit intent registers, contribution chains, claim hierarchy, argument maps…
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
map
Show or update the mapping between literature and thesis chapters — which sources support which arguments. Use for tracking coverage.