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 agentmods add skills/foliveira/harmonia/reviewnpx skills add foliveira/harmonia --skill reviewgit clone --depth 1 https://github.com/foliveira/harmoniaWrote 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/foliveira/harmonia/review)<a href="https://agentmods.dev/skills/foliveira/harmonia/review"><img src="https://agentmods.dev/badge/skills/foliveira/harmonia/review.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 | $0.00031 | $0.00596 |
| Opus 5 | $0.00015 | $0.00298 |
| Sonnet 5 | $0.00006 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
review 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 5d 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.
What it actually says
Your working contract is the 4 rules; their digest is injected at session start - read ${CLAUDE_PLUGIN_ROOT}/core/RULES.md in full only if that digest is not in your context.
Read the review stage from ${CLAUDE_PLUGIN_ROOT}/core/lifecycle.yaml (already in context if the flow runner loaded it - do not re-read) - the panel roster and lens name list live there and are authoritative - do not hardcode them (KTD11); each lens file under ${CLAUDE_PLUGIN_ROOT}/core/lenses/ carries its own trigger rules in frontmatter, which are authoritative for dispatch.
- Workspace:
bash ${CLAUDE_PLUGIN_ROOT}/bin/workspace.sh resolve --repo .(later stage: never mints; surface ambiguity or no-active-task and stop). - Gates before judgment:
bash ${CLAUDE_PLUGIN_ROOT}/bin/coverage/gate.sh --repo . --base <workspace base-ref> --workspace <ws>(soft block: uncovered lines flag the work incomplete; overrides go through--record-overrideand the audit log).bash ${CLAUDE_PLUGIN_ROOT}/bin/check-criteria.sh --run --workspace <ws> --repo .- executes every- run:criterion the scope declares, from the repo root, and prints the whole set it ran with each command verbatim. A failing criterion FAILS the review - this gate is hard, unlike coverage; exit 3 means there was no scope declaration to run. Keep the order: shipped criteria invoke the stage gates themselves, and--verify-receiptspasses only once a coverage receipt fresh for this tree is on disk.bash ${CLAUDE_PLUGIN_ROOT}/bin/coverage/gate.sh --verify-receipts --workspace <ws> --repo .- missing or stale receipts FAIL the review (tier B honesty, KTD7).
- Dispatch the reviewer (review lead) by path with every artifact this stage declares
in, plus the rest of the lead's charterconsumes:list - both are authoritative and neither is restated here (R9). The lead convenes the panel declared by this stage, dispatches lenses whose frontmatter triggers match the diff (security auto-fires on its fixed list), runs seats per${CLAUDE_PLUGIN_ROOT}/core/patterns/panel.mdwith model-diverse dispatch, and writes one attributedverdict.mdto the workspace. - A test-immutability violation recorded in the workspace is treated like a missing receipt: the review fails.
Pass workspace paths, not prose recaps (R8). Orchestrate only (R9).
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.
- 5d ago First seen · 18 lines · 31 tokens per session scan A c3d204af6890
review is a skill published in the GitHub repository foliveira/harmonia (2 stars, last pushed 20d ago), licensed MIT. It adds 31 tokens to every session and 596 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.
Other skills, from other repositories
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
clarify
Adaptive requirements clarification with auto-depth routing. Shallow (Q&A) for simple tasks, Deep (exploration + DRAFT + PLAN) for complex ones. Escalates automatically when ambiguity persists.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.