What is matilha-howl?

A read-only project-status reporter that reads status files and summarizes the current phase, active work streams, recent decisions, blockers, and next action. A work stream, or wave, is a group of related tasks tracked together.

Use it when you need to know where a project stands, what is happening now, what is blocked, or what to do next.

It answers project-state questions from recorded information instead of requiring someone to inspect several files manually. If the main status file is missing, it creates a minimal starting record.

matilha-howl — 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-howl

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-howl/github.svg)](https://agentmods.dev/skills/danilods/matilha-skills/matilha-howl)

Your own site

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

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 601 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	$0.00037	$0.00601
Opus 5	$0.00018	$0.00300
Sonnet 5	$0.00007	$0.00120
Haiku 4.5	$0.00004	$0.00060

Measured 12d ago against content hash 9bd38347ea5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

matilha-howl 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.

skills/matilha-howl/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When this fires

User asks "where am I?", "what's next?", "what's the state?", or similar intent. Read-only; no mutations. Works at any phase.

Preconditions

None. matilha-howl lazy-bootstraps project-status.md stub when absent, then reports on the stub.

Execution Workflow

Check project-status.md. If missing, write a minimal stub (current_phase: 0, phase_status: not_started, project_slug: <cwd basename>, next_action: "Run matilha-scout to begin discovery, matilha-plan to plan a feature, or matilha-init for fuller bootstrap"). Then read it via Read tool.
Parse frontmatter.
Read any docs/matilha/waves/wave-*-status.md files via Glob + Read; summarize (how many active, completed, failed).
Emit a streaming section listing: current_phase, phase_status, next_action, active_waves, recent_decisions (last 3), blockers.
If current_phase === 40 and a wave is in_progress, surface per-SP status per wave.
End with the next_action prompt from project-status.md.

Rules: Do

Keep output concise (≤ 50 lines).
Prioritize next_action.
Surface blockers prominently.

Rules: Don't

Modify any file (read-only).
Guess next_action (use the one in project-status.md).
Over-summarize if there are many waves (show them all).

Expected Behavior

User reads output and knows exactly what to do next without further questions.

Quality Gates

Output mentions current_phase, phase_status, next_action.
Active and completed waves enumerated.

Companion Integration

No companion integrations in Wave 4a.

Output Artifacts

None (read-only).

Example Constraint Language

Use "must" for: read project-status.md.
Use "must not" for: modify any file.
Use "may" for: include relative-time labels like "3 days ago" for stale phases.

Troubleshooting

"project-status.md missing": Instruct user to run /matilha-init.
"frontmatter invalid": Instruct user to restore via matilha init --force or manual fix.

CLI shortcut (optional)

Read the full file on GitHub · 71 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.

12d ago First seen · 71 lines · 37 tokens per session scan A 9bd38347ea5a

Subscribe to this mod's changes

matilha-howl is a skill published in the GitHub repository danilods/matilha-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 601 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 Project management agent-orchestration agentic-patterns ai-assisted-development anthropic claude-code-plugin matilha

matilha-howl