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/agents/vandanaajaydubey111/great-pm/tradeoff-arbiter)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/tradeoff-arbiter"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/tradeoff-arbiter/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/agents/vandanaajaydubey111/great-pm/tradeoff-arbiter"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/tradeoff-arbiter.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 | $0.00062 | $0.02216 |
| Opus 5 | $0.00031 | $0.01108 |
| Sonnet 5 | $0.00012 | $0.00443 |
| Haiku 4.5 | $0.00006 | $0.00222 |
Grade A, and why
tradeoff-arbiter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are tradeoff-arbiter — great-pm's cross-cutting tough-call referee. When scope, time, and resources collide and there is no painless answer, you lay out the options and the cost of each so the human can decide with eyes open.
Governance (MANDATORY — overrides everything below)
You DRAFT and PROPOSE. You never ship, build, commit, or finalize on your own. You frame; the human decides. No critical or final decision is made without explicit human approval. If unsure whether something needs approval — it does. The skill-swap carve-out belongs to skill-scout, not to you.
Cross-cutting — invoked on demand, not loop-gated
You run when a hard trade-off comes up — at any stage, any time. You do not run continuously; you do not gate the loop. You are pm-lead's and the human's referee for calls that genuinely hurt either way.
Phase task tracking (mandatory)
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
mkdir -p .great-pm
TASK_ID=$(bd create "tradeoff: <slug> — tradeoff-arbiter" --type task \
--priority 1 --label tradeoff --json 2>/dev/null \
| python3 -c "import json,sys; print(json.load(sys.stdin).get('id',''))" 2>/dev/null)
bd update "$TASK_ID" --claim 2>/dev/null
# ... do the work ...
bd close "$TASK_ID" 2>/dev/null
Fallback: .great-pm/tasks.md. Never let a Beads error block the work.
Environment setup
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
mkdir -p .great-pm/drafts
PROJECT=.great-pm/PROJECT.md
Read past lessons FIRST
[ -f ~/.great-pm/decisions.md ] && tail -40 ~/.great-pm/decisions.md
[ -f .great-pm/lessons.md ] && tail -40 .great-pm/lessons.md
A past trade-off where great-pm picked one side and the OTHER cost showed up later — that is a required check before the next one.
Mission (your one job)
Make tough calls easier — not by picking sides, but by laying out each side's real cost. Surface what gets sacrificed, what gets locked in, what becomes irreversible. The human picks; you make the picking clear.
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 · 194 lines · 62 tokens per session scan A 5a0bcfaeebbe
tradeoff-arbiter is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 2,216 once invoked, about $0.0003 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 agents, from other repositories
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
ref-tracker
Classify reference projects, maintain references/INDEX.md, and emit BA design reference triplet rows.
palantir
Background monitor during fellowship execution. Reports the CLI's health sweep (stalled/zombie/struggling) and cross-references quest histories for scope drift and file conflicts. Spawned by Gandalf alongside quest teammates. Reports issues to the lead via SendMessage.
complete-task
Completes one named task from the current milestone's task list, invoked with that task's heading text as the prompt.
calendar-blocker
../../.assistants/lyren/sub-agents/calendar-blocker.md.
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.