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/blendsdk/claude-codeops/exec_plannpx skills add blendsdk/claude-codeops --skill exec_plangit clone --depth 1 https://github.com/blendsdk/claude-codeopsWhat 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 | $0.00190 | $0.03027 |
| Opus 5 | $0.00095 | $0.01514 |
| Sonnet 5 | $0.00038 | $0.00605 |
| Haiku 4.5 | $0.00019 | $0.00303 |
Grade A, and why
exec_plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
exec_plan — Execute an Implementation Plan
CodeOps Skills Version: 3.20.0
Execute the implementation plan at plans/$ARGUMENTS/99-execution-plan.md. The first
argument is the feature name; an optional flag selects the commit mode.
This skill covers execution only. To create a plan, use the make_plan skill.
Resolve the plan path first (layout-aware)
Determine the layout via ../../_shared/layout-convention.md:
- Flat layout (no marker): the plan is at
plans/$ARGUMENTS/99-execution-plan.md— as flat layout always has. - Nested layout (marker present): the plan is under a feature —
codeops/features/<f>/plans/<plan>/99-execution-plan.md. If the target feature/plan is ambiguous, ask the user (never guess). A non-trivial task mini-plan lives at the same nested path and executes identically (see "Lightweight tasks" above). Everywhere below that saysplans/$ARGUMENTS/means this resolved plan path.
Commit modes
| Flag | Behavior |
|---|---|
(none) / --ask-commit |
Default. After each verified task, ask the user whether to commit. |
--no-commit |
Never commit, never ask. Pure implementation. |
--auto-commit |
Automatically commit + push (via /gitcmp) after each verified task. |
Full prompt wording, end-of-plan reminders, and commit-message format live in commit-modes.md — read it before the first commit decision.
Lightweight tasks (both layouts)
A non-trivial task has a single mini-plan at the resolved task path (flat:
plans/<task-slug>/99-execution-plan.md; nested:
codeops/features/<f>/plans/<task-slug>/99-execution-plan.md). Execute it exactly like a feature
plan — same per-task loop, same real-time update mandate, same commit modes — it is just a
smaller 99-execution-plan.md (objective + checklist + verify, no 00–07 set). Specification-first
ordering still applies when the task warrants tests (e.g. a bugfix's regression test).
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.
- 2d ago First seen · 210 lines · 190 tokens per session scan A e0a21f61ae71
exec_plan is a skill published in the GitHub repository blendsdk/claude-codeops (4 stars, last pushed 1mo ago), licensed MIT. It adds 190 tokens to every session and 3,027 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…