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-block-propagationgit 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-block-propagation)<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-block-propagation"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-block-propagation/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/thermiteau/maverick/mav-block-propagation"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-block-propagation.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 | $0.00054 | $0.00801 |
| Opus 5 | $0.00027 | $0.00400 |
| Sonnet 5 | $0.00011 | $0.00160 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
mav-block-propagation 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 12d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Block Propagation
When an agent-code-reviewer ejects a PR for human handling, every
downstream story that depended on it is transitively broken. Without
propagation, downstream stories keep branching off and stacking on top of
a broken base, producing PRs that cannot merge or merge into a broken
tree. The blocked-by:#N label is the mechanism that stops every
instance from trying.
Running a propagation
The entire marker-write-walk-clear protocol is one idempotent, resumable CLI command:
uv run maverick bprop run <repo> <epic> --ejected <story>
It writes the maverick-bprop marker on the epic, walks the DAG's
transitive descendants of the ejected story, applies blocked-by:#<story>
and posts a block comment on each (skipping any already labelled),
mirrors each story to blocked in the epic state, and deletes the marker
when the walk completes. Re-running after a crash resumes exactly where
the walk stopped — never perform the walk by hand.
If cold-start hydration finds a maverick-bprop marker on the epic, a
prior instance died mid-walk: re-run the command above with the marker's
ejected story before any other epic work. A partially-applied block
set invites downstream PRs to merge against a broken base.
Cancelling in-flight subagents
A block is useless if a subagent is already deep into a now-blocked story. After the walk:
- Check
.maverick/worktrees/for any worktree whose branch refers to a now-blocked story. - For each: stop the subagent, release its claim (see
mav-multi-instance-coordination), do not push its work. - Destroy the worktree. Do not attempt to salvage in-progress work — the base is broken; the work cannot be preserved usefully.
Block-on-entry checks
Three places must re-check block state at entry:
| Location | Check | Behaviour on block |
|---|---|---|
| Cold-start target resolution | Target has blocked-by:#N? |
Abort cleanly — report to user |
| Wave selection | Story has blocked-by:#N? |
Exclude from wave |
| Per-story re-verify (just before coding) | Story gained blocked-by:#N since wave start? |
Abort story; release claim |
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.
- 12d ago First seen · 80 lines · 54 tokens per session scan A 9801df746545
mav-block-propagation is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 801 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…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.