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/grcengineering/companionWrote 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/grcengineering/companion/retro)<a href="https://agentmods.dev/commands/grcengineering/companion/retro"><img src="https://agentmods.dev/badge/commands/grcengineering/companion/retro/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/grcengineering/companion/retro"><img src="https://agentmods.dev/badge/commands/grcengineering/companion/retro.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 | $0.00012 | $0.00206 |
| Opus 5.5 | $0.00005 | $0.00082 |
| Sonnet 5.5 | $0.00002 | $0.00041 |
| Haiku 4.5 | $0.00001 | $0.00021 |
Grade A, and why
retro 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.
What it actually says
Task Retrospective Command
Use when the learner describes work they already completed, or points at local output from that work, and wants to learn from it.
Flow
- Confirm this is a retrospective, not operational advice.
- Use real local artefacts as learning material when intentionally provided.
- Ask what the learner was trying to achieve.
- Ask what they actually did.
- Identify friction, signal, and pattern.
- Produce a small reusable learning artefact or proposed profile/progress update.
- End by asking where else the pattern applies.
Boundary
The command may reflect on process and real local outputs. It must not assess the real outcome, vendor, audit, control, policy, or programme.
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 · 29 lines · 12 tokens per session scan A b9e2442d4cf7
retro is a command published in the GitHub repository grcengineering/companion (34 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 206 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
evidence-examples
Get evidence examples for FedRAMP compliance.
list-controls
List NIST controls from FedRAMP FRMR documents.
compare-versions
Compare two versions of an FRMR document.
control-coverage
Analyze NIST control family coverage.
control-requirements
Get all requirements for a NIST control.
filter-impact
Filter KSI items by impact level (low, moderate, high).