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 thermiteau/maverick --skill mav-plan-executiongit clone --depth 1 https://github.com/thermiteau/maverickWrote 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/thermiteau/maverick/mav-plan-execution)<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-plan-execution"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-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 5.1 | $0.00066 | $0.01269 |
| Opus 5 | $0.00033 | $0.00634 |
| Sonnet 5 | $0.00013 | $0.00254 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
mav-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 8d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Execution
Execute an implementation plan step-by-step. Each step is implemented, verified, and committed before moving to the next. Progress is tracked durably on GitHub so it survives session loss.
Execution Mode
- Solo mode (called from do-issue-solo): work autonomously. Only pause when genuinely blocked or when the issue is ambiguous. Press through recoverable problems.
- Guided mode (called from do-issue-guided): provide checkpoints to the user. Pause when uncertain, report progress at natural break points.
Retry Budget (canonical)
Two fix attempts, then mav-systematic-debugging, then escalate per mode. This is the single retry budget for implementation work — other skills reference this rule rather than defining their own. If the same fix fails twice, the diagnosis is wrong: step back and think differently, never retry the same change a third time.
Execution Loop
1. Load the Tasks
Read the task list from one of:
- The tasks comment on the GitHub issue (if working from do-issue)
- The task list directly (if invoked standalone)
# The tasks comment id lives in the task-progress marker
uv run maverick task-progress read <repo> <issue> # -> .comments.tasks
gh api "repos/<repo>/issues/comments/<id>" --jq '.body'
2. Check for Prior Progress
If resuming after a crash or new session:
- Parse the checkboxes in the tasks comment (
- [x]= done,- [ ]= pending) - Cross-reference with
git log— if commits exist for tasks that aren't checked off, the comment update was lost. Check them off now (step 3.6). - Resume from the first genuinely unchecked task.
3. Execute Each Task
For each task in the list:
- Mark in-progress — note which task you are working on
- Implement — make the change described in the task
- Verify — run verification (lint, typecheck, tests) per the mav-local-verification skill
- Fix if needed — apply the retry budget above
- Commit — descriptive message referencing the issue number, using conventional commits
- Mark complete — check the task off durably:
The command is idempotent, edits exactly one checkbox, and goes through the App identity when configured. Never PATCH the comment body by hand.uv run maverick tasks check <repo> <issue> <n>
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.
- 8d ago First seen · 117 lines · 66 tokens per session scan A 2c38966c5ed0
mav-plan-execution is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,269 once invoked, about $0.0003 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.