agentmods.dev

matilha-hunt

matilha-hunt is a skill for Claude Code from danilods/matilha-skills. It costs 39 tokens per session (966 once invoked), scanned A, original, MIT.

A skill for dispatching a planned wave of subprojects by creating Git worktrees and kickoff files. A Git worktree is a separate working directory for another branch, allowing tasks to be worked on independently.

In plain words
What is it for?
Starting an execution wave, creating subproject branches and worktrees, writing status records, and printing the commands needed to begin each task.
Why use it?
It organizes parallel development and checks that tasks in the same wave will not edit the same files.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the matilha plugin — 12 skills, 10 commands, 2 agents, 1 hook shipped together

not rated 2repo 4mo ago A scan 39 tokens original MIT

Good fit Starting an execution wave, creating subproject branches and worktrees, writing status records, and printing the commands needed to begin each task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danilods/matilha-skills/matilha-hunt
View source ↗ danilods/matilha-skills
Install

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.

Any agent
npx skills add danilods/matilha-skills --skill matilha-hunt
Clone the repo
git clone --depth 1 https://github.com/danilods/matilha-skills

Made for: Claude Code.

Or install matilha, the plugin that ships this one along with the rest of its 12 skills, 10 commands, 2 agents, 1 hook.

Wrote 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.

agentmods badge for matilha-hunt

README.md
[![agentmods](https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-hunt/github.svg)](https://agentmods.dev/skills/danilods/matilha-skills/matilha-hunt)
Your own site
<a href="https://agentmods.dev/skills/danilods/matilha-skills/matilha-hunt"><img src="https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-hunt/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.

agentmods 80×15 button for matilha-hunt

Your own site · 80×15
<a href="https://agentmods.dev/skills/danilods/matilha-skills/matilha-hunt"><img src="https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-hunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 966 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00966
Opus 5 $0.00019 $0.00483
Sonnet 5 $0.00008 $0.00193
Haiku 4.5 $0.00004 $0.00097

Measured 11d ago against content hash 1e9cd9143c8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

matilha-hunt 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 11d 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.

skills/matilha-hunt/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When this fires

Plan exists (docs/matilha/plans/<slug>-plan.md) and user wants to enter Phase 40 execution. Skill sets up worktrees and wave-status bookkeeping; AI or user dispatches per-worktree sessions.

Preconditions

  • project-status.md shows current_phase ≥ 30.
  • Plan file exists.
  • Working tree clean.
  • Disjunction validated (intra-wave SPs touch disjoint files).

Execution Workflow

  1. Pre-flight (Swiss Cheese): resolve plan path, read project-status current_phase ≥ 30, verify clean tree via Bash git status --porcelain.
  2. Parse plan markdown (soft-strict: em-dash / colon / single-hyphen SP headings).
  3. Pick target wave (default wave 1, or --wave N).
  4. Validate disjunction (SPs in same wave must touch disjoint Touches lists); on violation throw 5-rule error unless --allow-overlap.
  5. Detect companions (superpowers via project-status.md:companion_skills.superpowers == "installed").
  6. Idempotency guard: if docs/matilha/waves/wave-NN-status.md exists and not --force, halt with recovery options.
  7. If --dry-run: emit preview and exit.
  8. For each SP: create branch wave-NN-sp-<slug> via Bash git branch, worktree ../<project>-sp-<slug> via Bash git worktree add, render kickoff.md + SP-DONE.md from templates (fetched via matilha pull from matilha-skills) via Write, write wave-status.md entry.
  9. Update .gitignore to include kickoff.md via Edit.
  10. Emit dispatch commands (one per worktree).

Rules: Do

  • Validate disjunction.
  • Gitignore kickoff.md.
  • Write wave-status before dispatch (bookkeeping survives partial failures).
  • Follow merge_order strictly in documentation.

Rules: Don't

  • Execute the SPs yourself (plugin only creates worktrees).
  • Force-merge (no --no-verify).
  • Modify project-status.md:current_phase.

Expected Behavior

N worktrees + N kickoff.md + N SP-DONE.md + 1 wave-status.md. User opens N terminals and pastes the dispatch commands.

Quality Gates

  • wave-NN-status.md exists and conforms to waveSchema.
  • Every SP entry has branch, worktree, status.
  • .gitignore contains kickoff.md.
  • current_phase ≥ 30 in project-status.md.

Read the full file on GitHub · 88 lines

Changes

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.

  1. 11d ago First seen · 88 lines · 39 tokens per session scan A 1e9cd9143c8c

Subscribe to this mod's changes

matilha-hunt is a skill published in the GitHub repository danilods/matilha-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 966 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 2026-08-31.

Claude CodeGit and workflowProject managementagent-orchestrationagentic-patternsai-assisted-developmentanthropicclaude-code-pluginmatilha
Related

Other skills, from other repositories

merge-review

Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.

SethGammon/Citadel · 40 tokens

team-release

Orchestrate the release team: coordinates release-manager, qa-lead, devops-engineer, and producer to execute a release from candidate to deployment.

Donchitos/Claude-Code-Game-Studios · 34 tokens

flo

MoFlo ticket spell - analyze and execute GitHub issues.

eric-cielo/moflo · 13 tokens

reset-epic

Reset an epic's test data — close PRs, delete branches, reopen issues, revert code.

eric-cielo/moflo · 24 tokens

close

End session with verification, commits, and documentation.

Kanevry/session-orchestrator · 11 tokens

gitlab-ops

Use this skill when performing VCS operations on GitLab or GitHub repositories — creating, updating, or closing issues and MRs, applying label taxonomy, running glab/gh CLI commands, or resolving project paths dynamically. Acts as the single source of truth for CLI command syntax and label conventions; consuming…

Kanevry/session-orchestrator · 174 tokens