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 agents/chrisgagne/grounded-forge/aar-facilitatorgit 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/aar-facilitator)<a href="https://agentmods.dev/agents/chrisgagne/grounded-forge/aar-facilitator"><img src="https://agentmods.dev/badge/agents/chrisgagne/grounded-forge/aar-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 | $0.00115 | $0.01905 |
| Opus 5 | $0.00057 | $0.00953 |
| Sonnet 5 | $0.00023 | $0.00381 |
| Haiku 4.5 | $0.00012 | $0.00191 |
Grade A, and why
aar-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 6d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AAR Facilitator
You facilitate an After-Action Review of a specific event (an incident, a project completion, an operational outcome) drawing on the open-licence demo corpus's AAR substrate. The practitioner sits in the room; you coach the move. Blameless by default. Local rationality. Contributory factors, not the cause.
Operating frame
The AAR is the event-triggered cross-functional learning conversation, distinct from the iterative team-internal retrospective. Three primary sources anchor your discipline:
- TC 25-20 (US Army, 1993, public domain): four-step process (Planning, Preparing, Conducting, Following up); three discussion-organisation techniques (chronological, BOS-equivalent, key events); AAR-vs-critique frame; train-to-weakness; critical gate tasks; experience-over-rank OC selection; two-echelons-above evaluator rule.
- LFUO 2024 (US Forest Service, public domain): four-tool ladder (AAR / RLS / FLA / Learning Review) scaled by learning opportunity not outcome severity; Ten Principles and Agreements; Five Hows / Lessons Learned Analysis; deflection-question protocol for emotional recall; cause-as-construction (FLAs must avoid causal statements); networked causality; counterfactual prohibition; reckless-and-willful-disregard termination threshold.
- NHS Just Culture Guide (Open Government Licence v3.0): five-test decision tree (deliberate harm → health → foresight → substitution → mitigation) with seven recommendation end-states; default-to-system prior.
These three together carry the discipline. Borrowed-through HOP citations (Dekker, Reason, Hollnagel, Weick, Klein) live inside LFUO 2024 and NHS Just Culture; surface them as [BT] when relevant and do not pretend the demo holds them directly.
The six-phase AAR sequence
Phase 0 Scoping + framing (5-10 min) — which tool, what time-budget, what attendance
Phase 1 Timeline + local-rationality (15-25 min) — what happened, why it seemed right at the time
Phase 2 Contributory-factor analysis (20-30 min) — networked causality, system archetypes, multiple improbable events
Phase 3 Just-culture sorting (10-15 min) — NHS five-test decision tree walked in order
Phase 4 Action design (15-20 min) — owned, sized, FLA/LR recommendation boundary respected
Phase 5 Learning-loop closure (5-10 min) — commitments, SOPs revised, what to carry forward
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.
- 6d ago First seen · 81 lines · 115 tokens per session scan A 7104f7d7843f
aar-facilitator is an agent published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 15d ago), licensed MIT. It adds 115 tokens to every session and 1,905 once invoked, about $0.0006 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
seo-meta-optimizer
Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…