What is matilha-gather?

A skill for bringing finished subprojects back into the main branch. It checks completion files, merges branches in a defined order, runs regression tests, and updates the wave status.

Validating completed subprojects, merging their Git branches without fast-forwarding, running tests after each merge, and recording the results.

It adds checks around parallel work so incomplete tasks or failed tests are caught before the changes are combined.

matilha-gather — Skill for Claude Code by danilods

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-gather

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-gather/github.svg)](https://agentmods.dev/skills/danilods/matilha-skills/matilha-gather)

Your own site

<a href="https://agentmods.dev/skills/danilods/matilha-skills/matilha-gather"><img src="https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-gather/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/danilods/matilha-skills/matilha-gather"><img src="https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-gather.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,182 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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.01182
Opus 5	$0.00022	$0.00591
Sonnet 5	$0.00009	$0.00236
Haiku 4.5	$0.00004	$0.00118

Measured 11d ago against content hash 33b7a7be0aee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

matilha-gather 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-gather/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When this fires

After /matilha-hunt dispatched a wave and every SP has written a filled SP-DONE.md, the user wants to merge them back and verify regression. This skill is the inverse of /matilha-hunt: it consumes wave-NN-status.md, validates gates, merges in order, runs tests after each merge, and updates status.

Preconditions

docs/matilha/waves/wave-NN-status.md exists and validates against waveSchema.
Current branch is the integration branch (not wave-NN-sp-*).
Working tree clean.
Every SP's SP-DONE.md passes strict gates.

Execution Workflow

Read docs/matilha/waves/wave-NN-status.md via Read tool; validate against waveSchema.
Swiss Cheese pre-flight via Bash: verify current branch is not an SP branch (git rev-parse --abbrev-ref HEAD); verify clean tree (git status --porcelain).
For each SP in merge_order where status is not completed: validate <worktree>/SP-DONE.md strict gates (status=completed, tests.passed=true, non-empty commits[], non-null completed_at, tests.count>=1, sp_id/feature/wave match).
If --dry-run: emit merge plan preview and exit.
For each SP in merge_order: git merge --no-ff <branch> via Bash; on conflict, run git merge --abort and HALT (5-rule error with conflicting files).
After each successful merge: run test command (default npm test via Bash); on failure, HALT (5-rule error with git reset --hard <pre-merge-sha> recovery).
Update wave-status: mark SP merged (status: completed).
After all SPs merged: mark wave completed, regression_status: passed, ended: .
If --cleanup: for each completed SP, git worktree remove --force <path> + git branch -d <branch>.

Rules: Do

Validate SP-DONE gates BEFORE any merge (all-or-nothing pre-flight).
Run git merge --no-ff (preserve merge commits as wave markers).
Run test command after every merge (localize regressions).
Commit wave-status.md after each mutation for atomicity.

Rules: Don't

Auto-rollback on failure (HALT preserves state for inspection).
Force-merge or skip regression.
Delete unmerged branches (safe -d, not -D).
Advance project-status.md current_phase (attest owns that).

Read the full file on GitHub · 89 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.

11d ago First seen · 89 lines · 44 tokens per session scan A 33b7a7be0aee

Subscribe to this mod's changes

matilha-gather is a skill published in the GitHub repository danilods/matilha-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,182 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 Code Git and workflow Releases Testing agent-orchestration agentic-patterns ai-assisted-development anthropic claude-code-plugin matilha

matilha-gather

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

When this fires

Preconditions

Execution Workflow

Rules: Do

Rules: Don't

What this file has done since we first saw it

Other skills, from other repositories

merging-to-main

finishing-a-development-branch

codew-release-qa-sweep

deploy-steward

changelog

team-release