review
Harmonia review stage - hierarchical review under the review lead with gates and receipts.
Skill by foliveira
Chalk Labs
Need help deploying review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/foliveira-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: sales
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/review
What's inside
- Skill name
review- Description
- Harmonia review stage - hierarchical review under the review lead with gates and receipts. Use ONLY when explicitly invoked as /harmonia:review.
- License
- MIT
- Instructions
- 13 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Your working contract is the 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; each lens file under `${CLAUDE_PLUGIN_ROOT}/core/lenses/` carries its own trigger rules in frontmatter, which are authoritative for dispatch.
1. Workspace: `bash ${CLAUDE_PLUGIN_ROOT}/bin/workspace.sh resolve --repo .` (later stage: never mints; surface ambiguity or no-active-task and stop).
2. Gates before judgment:
- `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; exit 3 means there was no scope declaration to run. Keep the order: the receipt audit passes only once a `criteria-run` receipt fresh for this tree is on disk.
- `bash ${CLAUDE_PLUGIN_ROOT}/bin/verify-receipts.sh --workspace <ws> --repo .` - missing or stale receipts FAIL the review.
3. Dispatch the reviewer (review lead) by path with every artifact this stage declares `in`, plus the rest of the lead's charter `consumes:` list - both are authoritative and neither is restated here. The lead convenes the panel declared by this stage, dispatches lenses whose frontmatter triggers match the diff (security auto-fires on its fixed list), runs seats per `${CLAUDE_PLUGIN_ROOT}/core/patterns/panel.md` with model-diverse dispatch, and writes one attributed `verdict.md` to the workspace.
4. A test-immutability violation recorded in the workspace is treated like a missing receipt: the review fails.
Pass workspace paths, not prose recaps. Orchestrate only.From foliveira/harmonia, MIT.
More from foliveira/harmonia
- 0.595score
onboard
foliveira
Harmonia onboard - capture an existing repo's canonical verify commands into .harmonia/project.yaml.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
capture
foliveira
Harmonia capture stage - record learnings into the right memory tier, then ship structured commits.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
discuss
foliveira
Harmonia discuss stage - turn a direction into pinned scope with checkable success criteria.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
ideate
foliveira
Harmonia ideate stage - generate and evaluate divergent directions before committing to one.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
implement
foliveira
Harmonia implement stage - red-green build, tests leading, under the criteria gate.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
status
foliveira
Harmonia status - a read-only readout of the active task's stage, markers, and receipts.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
remember
foliveira
Harmonia remember - capture a single learning into the right memory tier.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
flow
foliveira
Harmonia flow - run a pinned task through plan, implement, and review in one unattended pass, stopping at human acceptance.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
quick
foliveira
Harmonia express lane - implementer plus lead-solo review for trivial fixes.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
plan
foliveira
Harmonia plan stage - design how to build within the pinned scope.
SkillAFreshness: A★ 2Claude Code +9 - 0.549score
recall
foliveira
Harmonia recall - surface relevant past learnings for the current repo mid-session.
SkillBFreshness: B★ 2Claude Code +9 - 0.499score
reject
foliveira
Harmonia reject - record that the developer rejected the built work, blocking capture until it is re-accepted or abandoned.
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Sep 28, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/foliveira/harmonia
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from foliveira
- 0.595score
onboard
foliveira
Harmonia onboard - capture an existing repo's canonical verify commands into .harmonia/project.yaml.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
capture
foliveira
Harmonia capture stage - record learnings into the right memory tier, then ship structured commits.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
discuss
foliveira
Harmonia discuss stage - turn a direction into pinned scope with checkable success criteria.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
ideate
foliveira
Harmonia ideate stage - generate and evaluate divergent directions before committing to one.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
implement
foliveira
Harmonia implement stage - red-green build, tests leading, under the criteria gate.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
quick
foliveira
Harmonia express lane - implementer plus lead-solo review for trivial fixes.
SkillAFreshness: A★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
review skill. Agent Mart. https://agentmart.dev/skills/foliveira-review (last updated 2026-10-24)