coordinator-source-of-truth
Skill1.5k starsChanged 5 months agoMITView on GitHub
The complete file-by-file source-of-truth hierarchy for Squad: which files are authoritative, which are derived/append-only, who may write each one, who may read each one, and the precedence rules when they conflict. Squad coordinator loads this on demand when it needs to resolve a write conflict, decide where a piece of state belongs, or answer a 'who owns this file' question.
6 other projects use a version of this, 6 of them edited.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- github/squadedited, first seen Nov 8, 2026
- microsoft/github-vteam-industry-demosedited, first seen Oct 25, 2026
- kubefleet-dev/kubefleetedited, first seen Oct 8, 2026
- microsoft/fsi-banking-payments-dispute-resolution-acceleratoredited, first seen Aug 14, 2026
- github/gh-awedited, first seen May 27, 2026
- Azure/fleetedited, first seen Feb 7, 2026
Who's talking about microsoft/waza
- @matsuu.bsky.social“Go実装なんだな。”Bluesky · May 10, 2026 · 4 likes
- postfinance/devcontainer-features“Create a feature that installs waza (https://github.com/microsoft/waza)”GitHub · Aug 14, 2026 · 1 reactions
- @awakecoding.com“The tessl command-line tool uses server-side evals for the agent skills, so you don't have to figure out …”Bluesky · May 15, 2026 · 1 likes
- Azure/azure-sdk-tools“[Discussion][Benchmark] Benchmark framework selection”GitHub · Mar 30, 2026 · 1 reactions
- neilli-sable/dotfiles“Update dependency github:microsoft/waza to v0.40.0”GitHub · Nov 8, 2026
The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 50
Talked about on GitHub and Bluesky (50 times).
On GitHub · 48
- Aug 14, 2026Create a feature that installs waza (https://github.com/microsoft/waza) — postfinance/devcontainer-features1 reaction
- Mar 30, 2026[Discussion][Benchmark] Benchmark framework selection — Azure/azure-sdk-toolssays it tested it1 reaction · 5 comments
- Nov 8, 2026Update dependency github:microsoft/waza to v0.40.0 — neilli-sable/dotfiles0 reactions
- Nov 6, 2026自作 skill に評価(evals)と静的チェックを用意する — oddgai/dotfiles0 reactions
- Nov 2, 2026build(waza): bump pinned waza to 0.39.1 — akunzai/agent-skills0 reactions
43 more on GitHub
- Oct 13, 2026renovate(mise): Update dependency github:microsoft/waza to v0.38.9 — y-miyazaki/config0 reactions
- Oct 12, 2026build(waza): bump pinned waza to 0.38.10 — akunzai/agent-skills0 reactions
- Oct 9, 2026Update dependency github:microsoft/waza to v0.38.9 — neilli-sable/dotfiles0 reactions
- Oct 8, 2026[Candidate] microsoft/waza/examples/code-explainer - code-explainer — ProSkillsMD/proskills0 reactions · 1 comment
- Oct 8, 2026[Candidate] microsoft/waza/.copilot/skills/error-recovery - error-recovery — ProSkillsMD/proskills0 reactions · 1 comment
- Oct 8, 2026[Candidate] microsoft/waza/.copilot/skills/agent-collaboration - agent-collaboration — ProSkillsMD/proskills0 reactions · 1 comment
- Oct 8, 2026renovate(mise): Update dependency github:microsoft/waza to v0.38.8 — y-miyazaki/config0 reactions
- Oct 5, 2026chore(deps): bump waza to 0.38.9 — akunzai/agent-skills0 reactions · 1 comment
- Oct 4, 2026Clean up the Google Sheet so the graph gets real topics (Category values, duplicates, empty tabs) — Amitro123/knowledgeBase-Agent0 reactions · 3 comments
- Oct 3, 2026Update dependency github:microsoft/waza to v0.38.8 — neilli-sable/dotfiles0 reactions
- Oct 3, 2026chore: update dependency github:microsoft/waza to latest — daaa1k/skills0 reactions · 3 comments
- Sep 3, 2026renovate(mise): Update dependency github:microsoft/waza to v0.38.7 — y-miyazaki/config0 reactions
- Aug 23, 2026Update dependency github:microsoft/waza to v0.38.7 — neilli-sable/dotfiles0 reactions
- Aug 22, 2026renovate(mise): Update dependency github:microsoft/waza to v0.38.6 — y-miyazaki/config0 reactions
- Aug 19, 2026Update dependency github:microsoft/waza to v0.38.6 — neilli-sable/dotfiles0 reactions
- Aug 17, 2026spec: replace API paired evaluation with Waza (Copilot-native) — akunzai/agent-skills0 reactions
- Aug 14, 2026renovate(mise): Update dependency github:microsoft/waza to v0.38.5 — y-miyazaki/config0 reactions
- Aug 12, 2026Update dependency github:microsoft/waza to v0.38.5 — neilli-sable/dotfiles0 reactions
- Aug 3, 2026renovate(mise): Update dependency github:microsoft/waza to v0.38.4 — y-miyazaki/config0 reactions
- Jul 24, 2026renovate(mise): Update dependency github:microsoft/waza to v0.38.3 — y-miyazaki/config0 reactions
- Jul 15, 2026Review and improve Waza User Guide documentation — microsoft/vscode-chat-customizations-evaluation0 reactions · 1 comment
- Jul 15, 2026feat(battle-testing-a-skill): add 7 adversarial dimensions missing vs superpowers/waza/academic threat models — tvna/gitapexsays it tested it0 reactions
- Jul 13, 2026feat(evals): add waza eval suites for all skills lacking coverage — tvna/gitapex0 reactions
- Jul 13, 2026ci: add waza check as a non-blocking skill report — tvna/gitapex0 reactions
- Jul 8, 2026renovate(mise): Update dependency github:microsoft/waza to v0.38.0 — y-miyazaki/config0 reactions
- Jul 4, 2026skill周り整備 umbrella — happy663/dotfiles0 reactions
- Jun 25, 2026renovate(mise): Update dependency github:microsoft/waza to v0.37.0 — y-miyazaki/config0 reactions
- Jun 3, 2026ci(portable-pr-policy): cache prek, waza, and uv artifacts to speed up the all-files run — tvna/claude-md0 reactions · 1 comment
- Jun 3, 2026ci(portable-pr-policy): prek "against all files" step is slow (~110s cold) -- cache hook envs and waza — tvna/claude-md0 reactions
- Jun 1, 2026Waza user guide: Content feedback — microsoft/vscode-chat-customizations-evaluation0 reactions
- May 31, 2026waza example: — KazuCocoa/specialist-role-cards0 reactions
- May 23, 2026[FEATURE]: Improving the skills for kelp migration and development — BenSchr/kelp-core0 reactions
- May 10, 2026feat(evals): introduce microsoft/waza for skill quality evaluation — iwasa-kosui/kamae-ts0 reactions
- Apr 8, 2026feat(ci): waza-based skill quality checks (Phase 1) — PRD #812 — github/squad0 reactions · 6 comments
- Apr 6, 2026PRD: Skill Security Scanning — Markdown-Aware Scanner for Agent-Executable Instructions — github/squad0 reactions · 3 comments
- Apr 6, 2026feat: Adopt waza ComplianceChecker for skill security scanning — github/squad0 reactions · 1 comment
- Apr 4, 2026PRD: Waza-Based PR Quality Checks for Squad Skills — github/squad0 reactions · 3 comments
- Apr 4, 2026PRD: Waza-Based PR Quality Checks for Squad Skills — diberry/squad0 reactions · 1 comment
- Mar 29, 2026Clean up Copilot CLI session-state after eval runs — ronniegeraghty/hyoka0 reactions · 3 comments
- Mar 27, 2026apr may 2026 — kimtth/azure-openai-llm-notes0 reactions
- Mar 25, 2026Bootstrap azure-net-skills-scenarios for .NET SDK skills measurement using waza — JonathanCrd/azure-net-skills-scenarios0 reactions
- Mar 22, 2026feat: add Waza evaluation suite for skill quality validation — ahmadabdalla/azure-cost-calculator0 reactions · 2 comments
- Mar 5, 2026Skill quality validation against sensei/waza best practices — haileyvictory/azure-building-blocks0 reactions
On Bluesky · 2
- May 10, 2026Go実装なんだな。 — @matsuu.bsky.social4 likes and reposts
- May 15, 2026The tessl command-line tool uses server-side evals for the agent skills, so you don't have to figure out how to do it yourself. I didn't… — @awakecoding.com1 likes and repost
Used with
Projects with it also use e2e-template-testing, notification-routing and 8 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GitHubSkille2e-template-testing
End-to-end validation of coordinator and agent template changes
Also in 3 projects that use this
GitHubSkillnotification-routing
Route agent notifications to specific channels by type — prevent alert fatigue from single-channel flooding
Also in 3 projects that use this
Microsoft AzureSkillarchitectural-proposals
How to write comprehensive architectural proposals that drive alignment before code is written
Also in 3 projects that use this
Microsoft AzureSkillci-validation-gates
Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22
Also in 3 projects that use this
- +1 more from github
- +5 more from Azure
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 6
- github/gh-aw★ 5.6k82% same
- github/squad★ 3.4k81% same
- Azure/fleet★ 22782% same
- kubefleet-dev/kubefleet★ 16482% same
- microsoft/github-vteam-industry-demos★ 282% same
- microsoft/fsi-banking-payments-dispute-resolution-accelerator★ 082% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .squad/copilot-instructions.mdCopilot instructions
- .squad-templates/copilot-instructions.mdCopilot instructions
- .squad/templates/copilot-instructions.mdCopilot instructions
- squad-commandsSkill
- code-explainerSkill
- evidence-judgeSkill
- agent-collaborationSkill
- azd-publishSkill
- coordinator-init-modeSkill
- coordinator-response-modeSkill
- cross-squad-communicationSkill
- cross-squadSkill
- error-recoverySkill
- git-workflowSkill
- iterative-retrievalSkill
- reflectSkill
- reviewer-protocolSkill
- secret-handlingSkill
- session-recoverySkill
- squad-conventionsSkill
- squad-helpSkill
- squadSkill
- squad-version-checkSkill
- test-disciplineSkill
- tiered-memorySkill
- code-explainerSkill
- waza-interactiveSkill
- wazaSkill
- {skill-name}Skill
- squad-conventionsSkill
- {skill-name}Skill
- {skill-name}Skill
- squad-conventionsSkill
- waza-runnerSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Only an authorized coordinator or Scribe handles required persistence under the current state contract.
- Very specific: line 57
Waza casting repair: write authority does not permit raw registry/history edits.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Load this skill when: the coordinator (or any agent) needs to resolve a "where does this state belong?" or "who is allowed to write this file?" question — e.g., when about to write
.squad/decisions.md, when reviewing whether an agent broke the append-only rule, when answering a user question about Squad's file layout, or when adjudicating a conflict between two files. The short summary insquad.agent.mdis for routing; this skill is the full reference.
State backend note
Files below marked as "Derived / append-only" are mutable state — agents access them with runtime state tools (squad_state_read, squad_state_write, squad_state_append, squad_state_delete, squad_state_list). The runtime decides whether the configured backend stores them on disk, git-native state, or an external provider. Files marked as "Authoritative" are static config and always live on disk regardless of backend.
File hierarchy
Waza support-review override (Squad only): Charter output/persistence restrictions take precedence over generic history, audit-trail or decision-inbox write permissions below. Rai and Fact Checker return findings in the current review response. Only an authorized coordinator or Scribe handles required persistence under the current state contract; no routine review logging is required. Preserve existing historical records. Scribe remains bound by its charter: a decision-only Scribe cannot write logs, histories or audit trails. The Coordinator arranges any required non-decision persistence through an authorized writer; a missing writer is a blocker, not permission for Scribe. These coordination rules do not apply to ordinary Copilot work.
| File | Status | Who May Write | Who May Read |
.github/agents/squad.agent.md | Authoritative governance. All roles, handoffs, gates, and enforcement rules. | Repo maintainer (human) | Squad (Coordinator) |
.squad/decisions.md | Authoritative decision ledger. Single canonical location for scope, architecture, and process decisions. | Coordinator or coordinator-delegated Scribe; already-accepted decisions only, append only | All agents |
.squad/team.md | Authoritative roster. Current team composition. | Squad (Coordinator) | All agents |
.squad/routing.md | Authoritative routing. Work assignment rules. | Squad (Coordinator) | Squad (Coordinator) |
.squad/ceremonies.md | Authoritative ceremony config. Definitions, triggers, and participants for team ceremonies. | Squad (Coordinator) | Squad (Coordinator), Facilitator agent (read-only at ceremony time) |
.squad/casting/policy.json | Authoritative casting config. Universe allowlist and capacity. | Squad (Coordinator) | Squad (Coordinator) |
.squad/casting/registry.json | Authoritative name registry; paired transaction. Persistent agent-to-name mappings. | Squad (Coordinator), only via .squad/casting-transactions.md's locked SDK writer | Squad (Coordinator), paired read |
.squad/casting/history.json | Derived / append-only contents; paired transaction. Universe usage history and assignment snapshots. | Squad (Coordinator), only via the same paired writer | Squad (Coordinator), paired read |
.squad/casting/registry-history.commit.json | SDK-owned transaction/hash manifest. Never hand-edit or discard to bypass validation. | Locked SDK paired writer only | SDK paired reader |
.squad/agents/{name}/charter.md | Authoritative agent identity. Per-agent role and boundaries. | Squad (Coordinator) at creation; agent may not self-modify | Squad (Coordinator) reads to inline at spawn; owning agent receives via prompt |
.squad/agents/{name}/history.md | Derived / append-only. Personal learnings. Never authoritative for enforcement. | Owning agent only where charter permits; authorized Scribe for required context | Owning agent only |
.squad/agents/{name}/history-archive.md | Derived / append-only. Archived history entries. Preserved for reference. | Scribe | Owning agent (read-only) |
.squad/orchestration-log/ | Derived / append-only. Agent routing evidence. Never edited after write. | Scribe | All agents (read-only) |
.squad/log/ | Derived / append-only. Session logs. Diagnostic archive. Never edited after write. | Scribe | All agents (read-only) |
.squad/templates/ | Reference. Format guides for runtime files. Not authoritative for enforcement. | Squad (Coordinator) at init | Squad (Coordinator) |
.squad/rai/policy.md | Authoritative RAI policy. Check categories, terminology standards, and opt-out rules. | Squad (Coordinator) at init or authorized policy changes; Rai read-only | Rai, All agents (read-only) |
.squad/rai/audit-trail.md | Derived / append-only. Preserve existing redacted records; never raw secrets or harmful content; no routine reviewer logging. | Authorized Coordinator/Scribe only when the current state contract requires persistence | Rai, Squad (Coordinator) |
.squad/fact-checker/policy.md | Authoritative verification + Devil's Advocate policy. Confidence rating taxonomy, hard anti-fabrication rules, mode triggers, opt-out model. | Squad (Coordinator) at init or authorized policy changes; Fact Checker read-only | Fact Checker, All agents (read-only) |
.squad/fact-checker/audit-trail.md | Derived / append-only. Preserve existing succinct verdict/citation records, never raw source material; no routine reviewer logging. | Authorized Coordinator/Scribe only when the current state contract requires persistence | Fact Checker, Squad (Coordinator) |
.squad/plugins/marketplaces.json | Authoritative plugin config. Registered marketplace sources. | Squad CLI (squad plugin marketplace) | Squad (Coordinator) |
Rules
- If
squad.agent.mdand any other file conflict,squad.agent.mdwins. It is the only file with hard governance authority. - Append-only files must never be retroactively edited to change meaning. They are diagnostic and audit-trail material. Corrections go in a new entry that references the prior one.
- Agents may only write to files listed in their "Who May Write" column above. Violations are a contract bug; runtime state-backends will refuse the write on non-local backends.
- Non-coordinator agents may propose decisions in their responses. Coordinator alone accepts decisions; only the Coordinator or a coordinator-delegated Scribe may record already-accepted decisions in
.squad/decisions.md. - Waza casting repair: write authority does not permit raw registry/history edits. All casting mutations, including initialization and retirement, must commit the pair and manifest through
.squad/casting-transactions.md; use an equivalent atomic backend operation or stop on non-local storage. - Legacy is not a recovery fallback. SDK preparation validates existing state before callbacks. The known frozen v0.10 files require the guide's explicit approved archive-and-initialize maintenance procedure into an empty target; managed-pair corruption or a missing manifest must never trigger that path.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

