Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/adilkalam/orca/requirementsgit clone --depth 1 https://github.com/adilkalam/orcaWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00016 | $0.07895 |
| Opus 5 | $0.00008 | $0.03947 |
| Sonnet 5 | $0.00003 | $0.01579 |
| Haiku 4.5 | $0.00002 | $0.00789 |
Grade A, and why
requirements scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 955 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/requirements -- Requirements + Response-Aware Blueprint
Use this command to produce a blueprint-quality requirements spec for a task
before running any domain lane (/nextjs, /ios, /expo, etc.).
It combines:
- The OS 7.1 requirements pipeline (requirements folder + docs),
- Response Awareness tagging (RA tags as per
docs/concepts/response-awareness.md), - Cognition analysis (optional) for deeper problem understanding,
- ProjectContextServer for context-aware analysis.
You never implement code from /requirements; you only plan.
Step 0: Route Check
This is /requirements (planning), not a cognition/reasoning session.
- OUTPUT goes to:
.orca/requirements/(ALWAYS) - NOT to:
.orca/cognition/(that's for cognition sessions) - Cognition flags (--solve, --visual, --systems, etc.) are ANALYSIS INPUTS, not output destinations.
If you find yourself saving to .orca/cognition/ -- STOP. You are in the wrong pipeline.
CRITICAL: Requirements Folder First
REGARDLESS of any cognition flags (--visual, --systems, --solve, etc.):
- FIRST: Create the requirements folder at
.orca/requirements/YYYY-MM-DD-HHMM-slug/ - THEN: Run discovery questions (no cognition-mcp before AskUserQuestion)
- THEN: Run cognition analysis (if flagged) and save output INTO that folder
- THEN: Generate spec
Cognition analysis is an INPUT to the requirements process, not a replacement for it.
Never save /requirements output to .orca/cognition/ -- that directory is for cognition sessions only.
0.1 Parse Arguments
Tier Flags
/requirements supports four planning depths that match /orca-* execution tiers:
| Flag | Planning Depth | Use Case |
|---|---|---|
| (default) | Standard -- Full discovery + detail questions, complete spec | Most features |
--tweak |
Quick -- 2-3 scope questions, minimal spec | Small changes, config updates |
--complex |
Deep -- Extended analysis, risk assessment, multi-phase breakdown | Architecture changes, refactors |
--explore |
Exploratory -- Full divergent exploration, tentative brief | Half-baked ideas, early-stage thinking |
--solve |
Convergent -- Structured 8-step analysis before planning | Complex decisions, architectural choices |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 955 lines · 16 tokens per session scan A 93098026d438
requirements is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 7,895 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.