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/VandanaAjayDubey111/great-pmWrote 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/vandanaajaydubey111/great-pm/pm-burn)<a href="https://agentmods.dev/commands/vandanaajaydubey111/great-pm/pm-burn"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-burn/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/vandanaajaydubey111/great-pm/pm-burn"><img src="https://agentmods.dev/badge/commands/vandanaajaydubey111/great-pm/pm-burn.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 | $0.00033 | $0.00683 |
| Opus 5.5 | $0.00013 | $0.00273 |
| Sonnet 5.5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
pm-burn 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the great-pm /pm-burn command. Show the cost trend so the human can budget.
Parse $ARGUMENTS — N defaults to 30.
Operating procedure
-
Step 0 — refine the user's query (transparent Mode B). Invoke
query-refiner-pmwith$ARGUMENTS. The refiner returns:You typed: <original> Refined to: <refined brief> What changed: <one line> Proceeding with refined. Reply "use original" to override.Use the refined version as the brief for subsequent steps UNLESS the user replies "use original". Log the refinement to
.great-pm/refinements/$(date +%Y-%m-%d).log. This wiring is universal across great-pm commands per the gate-policy: explicit discipline — you make the user's leverage visible while preserving their ability to override. -
Count agent runs in the window from
.great-pm/verdicts/*.log. -
Estimate LLM cost using rough per-run rates (Opus-4.7 is great-pm's default):
- pm-lead / pm-reviewer / pm-auditor (orchestrators): ~$1–2 per run
- specialists (user-researcher, market-analyst, spec-writer, etc.): ~$0.50–1.50
- meta agents (continuous-learner, skill-scout): ~$0.30–0.80
-
Estimate human-equivalent for the same work:
- PM hours × $150 + researcher hours × $100 + analyst hours × $150 + 30% overhead.
-
Compute savings_x = human_total / llm_total.
-
Flag outliers — any agent with >2× its typical run count this period.
Output shape
great-pm burn — last <N> days
LLM cost: $<X> total
Human equivalent: $<Y>
Savings_x: ~<Z>× cheaper · ~$<saved> saved
Cost by agent:
pm-lead: <runs> × $<rate> = $<sub>
user-researcher: <runs> × $<rate> = $<sub>
...
Outliers (>2× normal):
<agent>: <runs> (normal <baseline>) — <hypothesis>
Reporting
- DONE:
DONE: burn for last <N> days — $<X> LLM vs $<Y> human-equiv (~<Z>× savings). - BLOCKED: when no verdicts exist to calculate from.
Notes
The rates above are rough order-of-magnitude. Treat the report as directional, not precise — it's a trend signal, not an invoice.
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 · 67 lines · 33 tokens per session scan A 774125b61009
pm-burn is a command published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 683 once invoked, about $0.0001 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
CLAUDE
Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services.
spend
Report llm-redact per-upstream spend, the share from fallback re-issues, and remaining monthly budget.
research
Professional equity research analysis with institutional-grade formatting.
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.