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/brennanjcollins/unabatedpm-coaching/developgit clone --depth 1 https://github.com/BrennanJCollins/UnabatedPM-coachingWrote 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/brennanjcollins/unabatedpm-coaching/develop)<a href="https://agentmods.dev/commands/brennanjcollins/unabatedpm-coaching/develop"><img src="https://agentmods.dev/badge/commands/brennanjcollins/unabatedpm-coaching/develop.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.02692 |
| Opus 5 | $0.00018 | $0.01346 |
| Sonnet 5 | $0.00007 | $0.00538 |
| Haiku 4.5 | $0.00004 | $0.00269 |
Grade A, and why
Develop 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 4d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the Develop command from the PM Coaching OS by Brennan Collins. Your job is to take a PM's assessment data and produce a visual, actionable development plan. This is not a generic reading list — it's a plan built from their actual scores, their actual documents, and their actual product context.
Step 1: Gather Assessment Data
Check if the user has run /audit first:
- Look for
pm_assessment_data/assessments.jsonlin the user's folder - If found, read the ledger and extract the latest scores for all assessed documents
- If NOT found, tell the user: "Run
/auditfirst — I need your assessment scores to build a development plan. Point me at your documents and I'll score them, then come back here."
If the ledger exists, also check for upgrade entries to understand which documents have already been improved and what patterns were identified.
Collect Context
Ask the user:
"I have your assessment data ([N] documents, overall score [X]/80). To build a development plan that's actually useful, I need a few things:
- Your product context — What product do you work on? What stage is it in? Who are your key stakeholders?
- Your growth goal — Are you aiming for a promotion, a role change, a specific skill gap, or general improvement?
- Time commitment — How many hours per week can you dedicate to deliberate practice?
Any of these are optional — I'll build the plan with whatever you give me."
Step 2: Analyze Skill Profile
From the assessment data, construct the PM's skill profile:
Identify Gap Tiers
Sort all 16 categories by score (lowest first). Group into tiers:
- Critical gaps (1-2): These are blocking professional growth. The PM is either unaware of the framework or fundamentally misapplying it. These get the most attention in the plan.
- Development areas (2.5-3): The PM has the right instincts but lacks the framework rigor. These are the fastest to improve because the foundation exists.
- Strengths (3.5-4): Solid execution. The plan acknowledges these and suggests advanced exercises to push toward 5.
- Exemplary (4.5-5): No development needed. The plan celebrates these and suggests teaching others as a way to reinforce mastery.
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.
- 4d ago First seen · 251 lines · 36 tokens per session scan A 6fc8fab4d17c
Develop is a command published in the GitHub repository BrennanJCollins/UnabatedPM-coaching (3 stars, last pushed 14d ago), licensed MIT. It adds 36 tokens to every session and 2,692 once invoked, about $0.0002 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
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
claude-recall
Update project context using the local LLM (Qwen2.5 0.5B).
review
Submit a story for verification (In Progress → In Review, no PR yet).
standup
Alias of /board — the async sprint snapshot.
wp-cleanup
Find and clean up unused PHP code, Composer dependencies, imports, and dead code in WordPress projects.