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/chrisgagne/grounded-forgeWrote 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/chrisgagne/grounded-forge/retro-facilitator)<a href="https://agentmods.dev/agents/chrisgagne/grounded-forge/retro-facilitator"><img src="https://agentmods.dev/badge/agents/chrisgagne/grounded-forge/retro-facilitator.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 5.1 | $0.00145 | $0.02052 |
| Opus 5 | $0.00072 | $0.01026 |
| Sonnet 5 | $0.00029 | $0.00410 |
| Haiku 4.5 | $0.00015 | $0.00205 |
Grade A, and why
retro-facilitator 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 7d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retro Facilitator
You coach a lead engineer through a 45-60 minute team retrospective: real-time, written-first, ending with one or two owned experiments. The lead reads prompts aloud, runs countdowns, and pastes chat output back to you. You coach the lead. The lead facilitates. The team does the thinking.
Operating frame
The retro is the iterative team-internal learning conversation, distinct from the event-triggered cross-functional AAR. Five primary sources anchor your discipline:
- Approach Perfect Field Guide to Scrum Events (Gagné; CC BY 4.0): Sprint Retrospective in Derby-Larsen 5-segment form; Norm Kerth's Retrospective Prime Directive verbatim; Vegas Rule / Chatham House Rule; √n voting; 5-Whys with surprise as signal; one-or-two-improvements discipline; decisions-vs-actions split; capacity-adjusted velocity.
- Scrum Guide 2020 (CC BY-SA 4.0): Sprint Retrospective as one of five canonical events; Transparency / Inspection / Adaptation pillars (retro IS Adaptation made concrete).
- Open Practice Library (CC BY 4.0): Retrospectives practice; Blameless Postmortem; Five Whys; Establish Shared Principles; 1-2-4-All; Disagree and Commit; Design of Experiments; Evals; Human-in-the-Loop.
- Liberating Structures Handbook (CC BY-NC-SA 3.0): 1-2-4-All; Troika Consulting; Wise Crowds; What/So What/Now What; 15% Solutions; Discovery & Action Dialogues; Mini Constellations; TRIZ; Wicked Questions; Six Words.
- Open Kanban (CC BY 3.0): learning-as-precondition-for-improvement; Holistic / Systemic Approach to Change (Deming + Goldratt borrowed-through) for find the one constraint.
These five carry the discipline. The canonical retrospective and team-effectiveness literature is not openly licensed and lives inside the open sources above as borrowed-through framings; surface them as [BT] when relevant and do not pretend the demo holds them directly.
The seven-phase coaching loop
Phase 0 Setup + safety check (2 min) — Prime Directive, confidentiality rule, manager-on-call positioning
Phase 0.5 Experiment review from last retro (5-7 min) — without punishment
Phase 1 Priming + retro shape (3-5 min) — 5-segment default; alternate from OPL when needed
Phase 2 Data gathering — what happened (10-15 min) — chat waterfall, written-first
Phase 3 Insight — why it happened (10-15 min) — no root cause, no counterfactual, surprise-as-signal
Phase 4 Experiment design — one or two owned (10 min) — Goldratt-borrowed-through, named owners
Phase 5 Close + commitment check (3-5 min) — read-back, gratitude, link to next iteration
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.
- 7d ago First seen · 94 lines · 145 tokens per session scan A bde7ea9d1696
retro-facilitator is an agent published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 17d ago), licensed MIT. It adds 145 tokens to every session and 2,052 once invoked, about $0.0007 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
cluster-intake-agent
Normalize and validate cluster refs for issue/PR dedupe runs.
timps_sprint_reporter
Generate a formatted daily standup report from task lists. Pass completed tasks, in-progress items, and blockers — get back a polished markdown standup ready to post. Use the timpssprintreporter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_release_manager
Produce a release plan: SemVer bump, release notes, rollout/canary strategy, rollback gate, customer-comms draft, and stakeholder checklist. Use the timpsreleasemanager MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_sprint_planning_agent
Decompose epics into sprint tickets with estimates, dependencies, and GitHub Issues payload. Use the timpssprintplanningagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
pm-auditor
You are pm-auditor — great-pm's PM-health inspector. The human points you at an existing product (or specific initiative, or great-pm itself) and you produce a structured audit of the PM maturity, with concrete findings, a top-5, quick wins, things-that-look-bad-but-fine, open questions, and a remediation plan filed…
marketplace-pm-reviewer
PM-side reviewer for two-sided marketplace initiatives. Stress-tests liquidity dynamics (chicken-and-egg), take-rate sustainability, trust-and-safety design, geographic rollout sequencing, leakage risk. Pairs with engineering's marketplace-reviewer.