sdd-pilot
AGENTS.md98 starsChanged 24 days agoMITView on GitHub
This checkout contains the framework source, not an installed downstream project. Maintain the framework directly; downstream lifecycle gates do not govern framework development. If the user requests execution of any /sddp-* command while this file is loaded, stop before running scripts, delegating agents, or modifying artifacts. Warn: SDD command blocked: framework-development AGENTS.md is loaded. Run this command in a downstream project installed from an SDD Pilot release archive, or in a staged consumer test fixture. Discussing, reviewing, editing, or testing…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository73 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- sddp-amendSkill
- sddp-analyzeSkill
- sddp-autopilotSkill
- sddp-checklistSkill
- sddp-clarifySkill
- sddp-devopsSkill
- sddp-devsetupSkill
- sddp-implement-qc-loopSkill
- sddp-implementSkill
- sddp-initSkill
- sddp-planSkill
- sddp-prdSkill
- sddp-projectplanSkill
- sddp-qcSkill
- sddp-regenSkill
- sddp-reverseengineerSkill
- sddp-specifySkill
- sddp-systemdesignSkill
- sddp-tasksSkill
- sddp-amendSkill
- sddp-analyzeSkill
- sddp-autopilotSkill
- sddp-checklistSkill
- sddp-clarifySkill
- sddp-devopsSkill
- sddp-devsetupSkill
- sddp-implement-qc-loopSkill
- sddp-implementSkill
- sddp-initSkill
- sddp-planSkill
- sddp-prdSkill
- sddp-projectplanSkill
- sddp-qcSkill
- sddp-regenSkill
- sddp-reverseengineerSkill
- sddp-specifySkill
- sddp-systemdesignSkill
- sddp-tasksSkill
- adr-authoringSkill
- artifact-conventionsSkill
- clarification-strategiesSkill
- compact-communicationSkill
- evidence-led-authoringSkill
- implementation-standardsSkill
- instructions-managementSkill
- markdown-compressionSkill
- plan-authoringSkill
- quality-assuranceSkill
- sdd-methodologySkill
- sddp-amendSkill
- sddp-analyzeSkill
- sddp-autopilotSkill
- sddp-checklistSkill
- sddp-clarifySkill
- sddp-devopsSkill
- sddp-devsetupSkill
- sddp-implement-qc-loopSkill
- sddp-implementSkill
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
If the user requests execution of any /sddp-* command while this file is loaded, stop before running scripts, delegating agents, or …
- Distinctive: line 24
Keep canonical workflows and host wrappers consistent.
- Very specific: line 26
Run node --test tests/*.test.mjs and node scripts/drift-report.mjs --context source --output .build/drift-report --strict after changes.
- Distinctive: line 28
Keep developer instructions and source-only templates out of release archives.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
SDD Pilot framework development
This checkout contains the framework source, not an installed downstream project. Maintain the framework directly; downstream lifecycle gates do not govern framework development.
Command guard
If the user requests execution of any /sddp-* command while this file is loaded, stop before running scripts, delegating agents, or modifying artifacts. Warn:
SDD command blocked: framework-development AGENTS.md is loaded. Run this command in a downstream project installed from an SDD Pilot release archive, or in a staged consumer test fixture.
Discussing, reviewing, editing, or testing command implementations is allowed. A command name quoted in documentation or a test is not an execution request. Do not load the downstream instructions into this session to bypass the guard.
Source layout
.github/sddp/workflows/: canonical command orchestration..github/skills/and.github/agents/: shared references and delegated roles..agents/,.claude/,.codex/,.opencode/,.windsurf/, and.github/prompts/: host wrappers. Preserve cross-host behavior when changing commands.scripts/andtests/: Node.js runtime, release tooling, and contract tests. Use Node.js 22 or newer.templates/downstream/AGENTS.md: downstream runtime context, installed as rootAGENTS.mdin every release archive. Preserve its contracts independently of this file.project-instructions.md: downstream governance template, not framework-development policy.
Maintenance
Keep canonical workflows and host wrappers consistent. Preserve artifact grammars, traceability IDs, and existing consumer behavior unless the requested change explicitly alters them. Never edit downstream fixture artifacts to hide a failing test.
Run node --test tests/*.test.mjs and node scripts/drift-report.mjs --context source --output .build/drift-report --strict after changes. For release changes, test all six host archives and their installed runtime context. Test pipeline execution in staged consumer projects, not this source checkout.
Keep developer instructions and source-only templates out of release archives. Do not publish, push, or tag a release without user authorization. Report changed behavior, test results, and remaining blockers concisely.
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.