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/HigorAlves/orcWrote 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/higoralves/orc/retro)<a href="https://agentmods.dev/commands/higoralves/orc/retro"><img src="https://agentmods.dev/badge/commands/higoralves/orc/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/higoralves/orc/retro"><img src="https://agentmods.dev/badge/commands/higoralves/orc/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 | $0.00052 | $0.01126 |
| Opus 5.5 | $0.00021 | $0.00450 |
| Sonnet 5.5 | $0.00010 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00113 |
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 2d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:retro
Look back at a coding session and improve the environment the next session runs in, not the code it produced.
A retro's output is a navigation pointer, a lint rule, a CI job, a coding standard, a slimmer steering file, a log the agent could not see. The code review already judged the code; this judges what made the code hard to get right.
Where it sits: the last step of the main flow (/orc:flow Phase 9 and /orc:debug offer it), and a standalone command after any session that went sideways.
Arguments
--session <branch>— look back at that.orc/<branch>/session instead of the current one.--transcript <path>— a session log on disk, read as a primary source once/clearhas emptied the conversation.--propose— run P1 then P5: calibration and candidate project-context rules.<what to look back on>— free text narrowing the retro: "the three red slices", "why QA took 40 minutes".
Preconditions
🛑 Tracker writes
P4 files issues on the tracker. The preview gate before it is hard-outward:
--autonever skips it.
⚠️ Caution
P4 commits applied candidates on the current feature branch, never on a protected branch.
- A
.orc/<branch>/session is optional. Without one, say so and work from the conversation and git log alone.
Phases
Modules live in orc:phases (references/retro/). Entering a phase, Read exactly its module.
| Phase | Module | Skipped when |
|---|---|---|
| 0 Detect context | resident, below | never |
| 1 Primary sources | orc:retro/P1 |
never |
| 2 Candidates | orc:retro/P2 |
never |
| 3 Present | orc:retro/P3 |
never |
| 4 Act | orc:retro/P4 |
the P3 gate selects no candidate |
| 5 Propose | orc:retro/P5 |
no --propose |
With --propose, run P1, then P5, and stop; P2 to P4 do not run.
Phase 0 — Detect context
- Resolve the session branch:
--session <branch>, elsegit branch --show-current. - If
${ORC_STATE_DIR}/<branch>/is missing, note it for P1. - Record
--transcript <path>and the free-text focus, when given. - Invoke
orc:writing-for-agents.
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.
- 2d ago Changed · +6 lines c14a1090c4bc
- 5d ago First seen · 89 lines · 52 tokens per session scan A dd25bc43edbd
retro is a command published in the GitHub repository HigorAlves/orc (7 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 1,126 once invoked, about $0.0002 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 2026-10-21.
Other commands, from other repositories
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
scout-work
Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).
ccc-status
Turn periodic progress updates for long sessions on or off, choose the channel (Slack, Discord, email or console), interval and detail level, or send one now. Use when the user asks to be kept posted, pinged on progress, or to stop updates.
ccc-teleport
Move work between devices: pull a Claude Code on the web session into this terminal with teleport, or keep a local session controllable from the web or mobile app with Remote Control. Use when switching device, monitoring a long task from a phone, or resuming a cloud session locally.
ccc-cloudcli
Open, inspect or start CloudCLI web sessions so Claude Code is reachable from a browser or phone. Use when the user asks for web or mobile access to a running session.