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.
git clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/shaheerkhawaja/productionos/writing-plans)<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/writing-plans"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/writing-plans/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/writing-plans"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/writing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00028 | $0.00485 |
| Opus 5 | $0.00014 | $0.00243 |
| Sonnet 5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
writing-plans 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 12d 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.
What it actually says
/writing-plans — Implementation Planning
Turn approved designs into step-by-step executable plans.
Step 0: Preamble
Run templates/PREAMBLE.md. Read the spec or latest brainstorming output.
Step 1: Capture the Approved Scope
Restate the approved design, goal, and constraints before decomposing the work into tasks.
Plan Structure
1. Requirements Summary
- What are we building? (1-2 sentences)
- What are the success criteria?
- What are the constraints?
2. Task Breakdown
For each task:
### Task N: {title}
**Files:** {files to create/modify}
**Dependencies:** {tasks that must complete first}
**Effort:** S | M | L
**Risk:** Low | Medium | High — {why}
**Acceptance criteria:** {how to verify it's done}
3. Dependency Graph
Task 1 (foundation)
├── Task 2 (depends on 1)
├── Task 3 (depends on 1)
│ └── Task 5 (depends on 3)
└── Task 4 (independent)
4. Execution Strategy
- Which tasks can run in parallel?
- What's the critical path?
- Suggest
/auto-swarm-nthfor parallel tasks
5. Risk Matrix
| Risk | Likelihood | Impact | Mitigation |
|---|
6. Verification Plan
How do we know it's done? Tests to write, checks to run, criteria to meet.
Self-Eval
Run templates/SELF-EVAL-PROTOCOL.md on plan quality:
- Are all requirements covered by at least one task?
- Are dependencies mapped correctly?
- Is the critical path identified?
- Are risks realistic, not hand-waved?
Next Step
After plan approval: dispatch /auto-swarm-nth for parallel execution or work through tasks sequentially.
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.
- 12d ago First seen · 68 lines · 28 tokens per session scan A 2e3c9e117cdd
writing-plans is a command published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 485 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
rekindle
Recover a fellowship after a session crash. Scans worktrees and quest state, presents a recovery dashboard, and re-spawns Gandalf with recovered quest context. Use when returning to a crashed or expired fellowship session.
settings
View or edit fellowship configuration (/.claude/fellowship.json). Run /settings to see current settings, change values, or reset to defaults.
validate-docs
Validate that site and README documentation is current. Report-only — flags issues without modifying anything.
chronicle
One-time codebase onboarding — interactively extracts your team's conventions, identifies reference files, and generates CLAUDE.md sections so Claude codes the way your team does. Run once per project.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
red-book
Use after receiving PR review feedback. Extracts conventions from reviewer comments and offers to add them to CLAUDE.md. Closes the convention learning loop.