source-command-hdd-hdd
Skill64 starsChanged 4 months agoMITView on GitHub
[DEPRECATED] Thin HDD router — use /hdd skill instead
In this repository102 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- assumptionsSkill
- capture-learningSkill
- Codex-opus-4-6-promptingSkill
- Codex-promptSkill
- mcp-code-modeSkill
- deploy-team-hubSkill
- diagramSkill
- distillSkill
- effect-tsSkill
- escalateSkill
- evalSkill
- experimentSkill
- hddSkill
- hub-auditSkill
- hub-collabSkill
- implementSkill
- knowledgeSkill
- peer-notebook-delivery-guardSkill
- research-taskSkill
- session-reviewSkill
- source-command-hdd-decideSkill
- source-command-hdd-researchSkill
- source-command-hdd-stage-adrSkill
- source-command-hdd-validateSkill
- statusSkill
- supabaseSkill
- synthesizeSkill
- tasteSkill
- teamSkill
- test-suiteSkill
- theseus-protocolSkill
- thoughtbox:debugSkill
- thoughtbox:decisionSkill
- thoughtbox:evolutionSkill
- thoughtbox:knowledge-querySkill
- thoughtbox:onboardSkill
- thoughtbox:refactorSkill
- thoughtbox:researchSkill
- thoughtbox:session-reviewSkill
- thoughtbox-teamSkill
- ulc-loopSkill
- ulysses-protocolSkill
- workflow-brainstormingSkill
- workflow-ideationSkill
- workflow-reflectionSkill
- workflow-revisionSkill
- workflows-compoundSkill
- workflowSkill
- workflows-planSkill
- workflows-reviewSkill
- workflows-workSkill
- workflow-tournamentSkill
- assumptionsSkill
- capture-learningSkill
- claude-opus-4-6-promptingSkill
- claude-promptSkill
- mcp-code-modeSkill
- deploy-team-hubSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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 8
Use this skill when the user asks to run the migrated source command hdd-hdd.
- Very specific: line 14
This command is deprecated: Use the /hdd skill at .Codex/skills/hdd/SKILL.md instead.
- Distinctive: line 24
Run Hypothesis-Driven Development using small delegated modules.
- Distinctive: line 56
Run user checkpoint after each phase.
- Distinctive: line 62
After research: approve hypotheses.
- Distinctive: line 63
After stage ADR: approve implementation scope.
- Distinctive: line 64
After validate: confirm manual verification findings.
- Distinctive: line 65
Before decision: confirm accept/reject action.
≈ “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
source-command-hdd-hdd
Use this skill when the user asks to run the migrated source command hdd-hdd.
Command Template
/hdd (DEPRECATED)
This command is deprecated. Use the /hdd skill at .Codex/skills/hdd/SKILL.md instead.
The skill is the canonical HDD entry point with full sub-agent delegation templates,
spec creation, reconciliation dispositions, and --phases support for /workflow integration.
The module briefs in ./modules/ remain as reference material for sub-agent context.
Original description (preserved for reference)
Run Hypothesis-Driven Development using small delegated modules.
Usage
/hdd <adr-number> "<title>" [--resume]Instruction Budget
- This orchestrator is router-only and must stay under the orchestrator budget policy.
- Execution details live in phase modules.
Inputs
adr_number(required)title(required)resume(optional)
Delegation
- Research ->
./modules/research-brief.md - Stage ADR ->
./modules/stage-adr-brief.md - Implement ->
./modules/implement-brief.md - Validate ->
./modules/validate-brief.md - Decide ->
./modules/decide-brief.md
Orchestrator Steps
- Initialize or resume state.
- Delegate current phase using the standard handoff schema.
- Collect module output and persist phase result.
- Run user checkpoint after each phase.
- Append delegation trace event.
- Route to next phase until complete.
Checkpoints
- After research: approve hypotheses.
- After stage ADR: approve implementation scope.
- After validate: confirm manual verification findings.
- Before decision: confirm accept/reject action.
Output
- Accepted ADR migrated to production path, or rejected ADR archived with rationale.
- Workflow summary with outcomes and open risks.
- Trace artifact at
.Codex/command-traces/hdd.jsonl.
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.