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/aquivalabs/speccy/plan-executionnpx skills add aquivalabs/speccy --skill plan-executiongit clone --depth 1 https://github.com/aquivalabs/speccyWrote 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/aquivalabs/speccy/plan-execution)<a href="https://agentmods.dev/skills/aquivalabs/speccy/plan-execution"><img src="https://agentmods.dev/badge/skills/aquivalabs/speccy/plan-execution.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.02768 |
| Opus 5 | $0.00018 | $0.01384 |
| Sonnet 5 | $0.00007 | $0.00554 |
| Haiku 4.5 | $0.00004 | $0.00277 |
Grade A, and why
plan-execution 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 4d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Execution
Break an approved plan into tasks sized for a single agent context window, then execute them as subagents. Sequential tasks run directly on the main checkout; parallel tasks use git worktrees for isolation and are squash-merged back afterward.
If the plan fits a single context window, still use this skill: it produces one task and executes directly.
Prerequisites
Verification tools
Check that CLAUDE.md documents the project's verification tools (build, lint, static analysis, test commands). Execute agents rely on these to validate their work. If they're missing, tell the user: establishing verification standards comes before running a plan.
Worktree init
Worktree init is only needed when the plan has parallel tasks (which use git worktrees). If the plan is purely sequential, skip this section.
Worktrees must branch from the current HEAD so that parallel tasks see work committed by prior sequential tasks. Check .claude/settings.json for "worktree": { "baseRef": "head" }. If missing, add it (via Bash/python, since direct Edit on that file is blocked). The default (fresh) branches from origin/<default-branch>, which misses all feature-branch commits.
Check whether CLAUDE.md has a ## Worktree init section. If it does, resolve the gather/apply variables before running the workflow:
- Parse the Gather block, where each line has the form
NAME—command. Run each command via Bash in the main checkout and capture its stdout (trimmed). - Parse the Apply block, where each line is a shell command that may reference
${NAME}variables from the gather step. Substitute the gathered values into each command. Make symlink commands idempotent: replaceln -swithln -snfso re-runs don't create circular symlinks inside the existing target. - Pass the resolved commands as the
worktreeInitarg (string array) to the workflow.
If the section is missing and the plan has parallel tasks, tell the user. Worktree agents without init commands will lack gitignored state, which causes build failures, missing configs, and mid-task recovery friction. Offer to help draft the section before proceeding, the same way you would for missing verification tools.
What ships with it
5 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.
- 4d ago First seen · 120 lines · 36 tokens per session scan A 2b17ff507aa3
plan-execution is a skill published in the GitHub repository aquivalabs/speccy (11 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 2,768 once invoked, about $0.0002 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
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.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…