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/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/audit)<a href="https://agentmods.dev/commands/brennanjcollins/unabatedpm-coaching/audit"><img src="https://agentmods.dev/badge/commands/brennanjcollins/unabatedpm-coaching/audit/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/brennanjcollins/unabatedpm-coaching/audit"><img src="https://agentmods.dev/badge/commands/brennanjcollins/unabatedpm-coaching/audit.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 | $0.00040 | $0.05027 |
| Opus 5.5 | $0.00016 | $0.02011 |
| Sonnet 5.5 | $0.00008 | $0.01005 |
| Haiku 4.5 | $0.00004 | $0.00503 |
Grade A, and why
Audit 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 1mo 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 — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running a comprehensive PM skills audit using the Four Pillars framework from The Influential PM course by Brennan Collins. Your job is to evaluate real PM deliverables — not have a conversation about frameworks. Read the documents, score them, generate a visual dashboard, and report what you find.
Step 1: Gather Input
Ask the user to point you at their work:
"Point me at your PM deliverables — a folder of documents or a specific file. I'll read everything, score your work across the Four Pillars (16 skill categories, each rated 1-5), and generate a visual assessment dashboard.
This works best with real work product: strategy docs, PRDs, business cases, pitch decks, OKR docs, journey maps, demo scripts, stakeholder updates, competitive analyses, go-to-market plans.
Where should I look?"
Once the user provides a path (folder or file), proceed to Step 2.
Step 2: Scan and Read Documents
Folder Scanning
If the user provides a folder path, list all files and identify supported formats:
Supported formats:
.docx— Read viapandoc -f docx -t markdown [file]. If pandoc unavailable, trypython3 -c "import docx; ..."with python-docx..pptx— Read viamarkitdown [file]. If unavailable, trypython3 -c "from pptx import Presentation; ..."with python-pptx to extract text from slides..pdf— Read viapdftotext [file] -. If unavailable, trypython3 -c "import pdfplumber; ..."..md,.txt— Read directly.
Skip: Images, videos, spreadsheets, .DS_Store, hidden files, anything in pm_assessment_data/ or .pm_tmp/.
For each document read:
- Extract the full text content
- Note the file format (docx/pptx/pdf/md/txt)
- Note the file path (relative to the user's folder)
- Compute a content hash for deduplication. Preferred method — run:
If python3 is unavailable, fall back to a lightweight fingerprint: take the first 500 characters of the extracted text, lowercase, strip whitespace, and prefix withpython3 -c "import hashlib,sys; print('sha256:'+hashlib.sha256(open(sys.argv[1],'rb').read()).hexdigest())" "[file_path]"fp:— e.g.,fp:thisisthefirst500chars...
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.
- 1mo ago First seen · 475 lines · 40 tokens per session scan A 485dc97ae648
Audit is a command published in the GitHub repository BrennanJCollins/UnabatedPM-coaching (5 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 5,027 once invoked, about $0.0002 per session on Opus 5.5. 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
cs-internal-comms
Internal-only change-management comms using ADKAR (Prosci) + Kotter's 8-step. NOT marketing (external) and NOT executive narrative strategy. Direct invocation of the internal-comms skill.
cs-knowledge-ops
Company SOP + runbook authoring with 5W2H completeness checks. NOT personal PKM (that's llm-wiki). NOT engineering-specific runbooks. Direct invocation of the knowledge-ops skill.
cs-process-map
Map an internal business process (BPMN-style swim lanes), measure cycle time, and detect bottlenecks where work spends most of its time waiting. Direct invocation of the process-mapper skill.
project-health
Audit and manage project configuration — permissions, context, docs.
tasks
../../vertical-plugins/scenarios/commands/tasks.md.
refresh
Auto-enumerate the agent-runnable To-Do set and write it to state/todo-ids.json. No arguments. The operator's only job upstream is to mark rows in Notion with Exec=Agent; refresh then fetches them via the Notion REST API and the sidecar is the enumeration substrate for run.