Squad-Spec-Repository-Template
Template for spec-driven development with AI agents: a shared squad, one rule set for Claude, Codex and Copilot, and profiles for .NET, Go and Node.
Overview
The Squad-Spec-Repository-Template bundles everything a repository needs to work with AI agents: a team of fixed roles, a single rule set and the scaffolding for documentation and GitHub. It consists of a stack-neutral core plus one profile per technology stack. It is not used through GitHub’s “Use this template” button; the adopt-template skill applies it to an existing or new repository and refreshes it there later.
The squad runs through the skills squad-issue for bug fixes and squad-spec for new features. The flow: plan, challenge, security review, tests first, implementation to at least 80 % coverage, format and analyzer gate, review loop, Lead approval and finally the pull request.
CLAUDE.md for Claude Code, AGENTS.md for Codex and .github/copilot-instructions.md for GitHub Copilot are identical from their first ## heading on. The same goes for the skills create-pr, review-pr, squad-issue and squad-spec, which exist in all three environments.
Files in a target repository come in three kinds: managed files are overwritten on every refresh, marked files are rebuilt and keep their project blocks, and seed files are written once and never touched again. That keeps the core stack-neutral and means project-specific knowledge survives a refresh. Placeholders of the form {{TODO: …}} make config-check.py fail until they are filled in.
Features
Releases
v2026.11.12 · 15/11/2026
- [Core]
squad-log.py --helpsays--continued-fromtakes the step of a logged continuation too (#426) - [Core] A Lead decision on a failed manual test that orders no code is stamped again instead of looping through the
- [Core] After the Lead's decision on a failed manual test,
squad-next.pyholds the review until the work it ordered - [Core]
squad-next.pycounts a skeleton row's Files glob, directory or bare file name as changed when a matching - [Core] A plan-ordered review finding applied verbatim (
[NON-BLOCKING, plan, verbatim], or an untagged verbatim row - [Core] A manual test that fails at step 7 goes to the Lead, who adds a task group; after the group's stamp
- [Core] A task group a Lead decision adds in steps 7–8 is logged under its own steps 4–6, never
8 Fix; `squad-log.py - [Core] A group's coverage pass ends with a passing full stamp after its implementation, and a deferred test whose
- [Core] Commits that only save work end with
[skip ci]; the stamped, reviewed and ready heads never do, and - [Core] Members run Format in the foreground under a time limit, on the changed files where the formatter takes
- [Core] The Lead checks every planned signature against the analyzer's limits, sweeps every list of a set the change
- [Seed] dotnet
ci.ymlgrantschecks: writeto the build job only (githubactions:S8233);.squad/stack.mdlists
v2026.11.11 · 14/11/2026
- [Core] A
manual:check that names the Reviewer or Security runs in its step-8 round, not as a step-7 test, andplan-check.pyrefuses one that names a member outside the tier's review round; a Product Manager's manual check named only in the plan's prose holds the review, and an Orchestrator7 Manual testrow records a stand-in's (#396) - [Core] A member's report re-sent word for word after a task notification is part of its round, not a continued launch; members send their report once, with no background command left running (#397)
- [Core]
squad-log.pynames--round 1when a round is logged late;squad-next.pyasks for the verbatim row before stamping a documentation-only fix of an open review round that no Dev or Tester fix followed (#398) - [Core]
plan-check.pyskips appended challenge and security notes in its placeholder check; notes the Lead answered in Challenge are not asked for again (the template's own Challenge text answers none) (#401) - [Core] Security's diff verdict counts its non-blocking findings (
VERDICT: APPROVED | NON-BLOCKING n, else its tags), so tiersdocsandpatchdecide them before the PR; thepatchtest is written on the unfixed head before the edits (#402) - [Core]
squad-notes.pywrites a report's control characters as text escapes, so appended notes never failplan-check.py(#400) - [Core] The Dev's skeleton report lists the changed files from
git statusand only members read back from disk, andsquad-next.pysends a file a skeleton task row names but the branch has not changed back to the Dev before tests first; a plan names the test seam of a resource bound over an external system (#399) - [Core]
lesson-label.pycounts only the tools the template ships to.squad/tools/as managed, so a repository's own tool there is labelledsquad; Template-managed files names the template blocks of.editorconfigas marked (#395) - [Core]
result.mdis listed in the work folder (specs/README.md, Work folder) and posted in the working record of tiersdocsandpatch(#394) - [Profile] The seeded CI of every profile runs
decision-check.py --require-history --tags-fetchedin a jobdecision-records, so a changed released record cannot merge, and a refresh adds the job to an existing CI; a CI merged from several profiles runs it once and renames a prefixed job inneeds:too (#403) - [Profile] dotnet: the shared global analyzer config sets MSTEST0001, a rule reported without a location that no
.editorconfigsection reaches, toerror;dotnet-rules.pywrites a pending entry for such a rule into.squad/dotnet-rules-pending.globalconfigat a higherglobal_level, anddotnet_config.pychecks thatDirectory.Build.props, Dockerfiles and.dockerignorecarry both global configs (#393) - [Profile] dotnet:
.squad/dotnet-rules-pending.globalconfigkeeps the line ending of its checkout, so a CRLF repository's fresh clone passes the Analyzer gate;scope-check.pylets a product PR change it withsquad_settings.py, from which it is generated (#406)
v2026.11.10 · 13/11/2026
- [Skill]
adopt-templateasks for the Fork scope repository settings only in the pull request that adds - [Core] New
lesson-label.pynames a squad lesson's label from the files its fix changes (squad-upstreamfor a - [Core]
squad-next.pyreads a non-blocking count in the verdict clause only, so "no blocking or non-blocking - [Core]
session-usage.pycounts the harness's reply to aSubagentHandbackcall as part of the same round, so one - [Core] One Lead revision logged as the plan-check revise answers a challenge and a CHANGES_REQUIRED that came back
- [Core]
squad-next.pynames the fresh Leaddecidelaunch of step 6; a member's report is one final reply (#383) - [Core] A Reviewer verdict on a later head that adds only documentation to the stamped code counts; a criterion
- [Core] Tier
trivialkeeps a task group's order whentasks.mdputs the Tester first; a reason for the spec's - [Core] The Lead's result of tiers
docsandpatchis written verbatim toresult.mdwith `squad-notes.py - [Core] The Tester keeps test code, table tests included, under the analyzer's cognitive-complexity limit (#384)
- [Profile] dotnet: the Analyzer gate reports a diagnostic without a location (MSTEST0001) for its project when a
- [Seed] dotnet
UNIT_TESTS.mdnames the branch conditions the Coverage gate prints; gostack.mdsaysgocognit
v2026.11.9 · 12/11/2026
- [Docs] Mark PiMonitor as an active consumer
- [Core] Apply a challenge note's exact plan edit when appending it
- [Core] Take test names only from a cell's listed spans; check a waiting PR from a worktree
- [Skill] Split a seeded process record the project extended in place
- [Profile] Check that the image build sees the global analyzer config
- [Core] Work the open squad lessons and harden the seeded workflows
- [Core] Fix what the release rehearsal of the squad-lesson changes found
- [Docs] Release v2026.11.9
v2026.11.8 · 12/11/2026
- [Profile] Lower pending rules the dotnet baseline does not set
- [Profile] Switch baseline rules off in Razor code and fix rollout defects
- [Profile] Lower pending rules that only a section of paths sets
- [Docs] Release v2026.11.8
![[ e-networld.de ]](/img/logo.png)