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/Langerrr/zforgeWrote 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/langerrr/zforge/retro)<a href="https://agentmods.dev/commands/langerrr/zforge/retro"><img src="https://agentmods.dev/badge/commands/langerrr/zforge/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/langerrr/zforge/retro"><img src="https://agentmods.dev/badge/commands/langerrr/zforge/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 | $0.00009 | $0.00405 |
| Opus 5.5 | $0.00004 | $0.00162 |
| Sonnet 5.5 | $0.00002 | $0.00081 |
| Haiku 4.5 | $0.00001 | $0.00040 |
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
/retro — Zforge Workflow Retrospective
Evaluate how well zforge's workflow scaffolding served a feature. Output feeds plugin improvement, not project documentation.
Arguments
$1: Feature name (snake_case or will be converted)
Pre-flight
- Convert feature name to snake_case.
- Read
docs/{feature_name}/session_log.md. If not found or empty (no entries), stop: "No session history to evaluate. Run /retro at the end of a working session." Also readdocs/{feature_name}/decision_review.md§B if it exists — process notes written live during the run are the primary input, and they beat reconstructing the run from its artifacts afterwards. - Check current session context. If this is a fresh session with no substantial conversation about the feature (no prior tool calls touching feature files, no implementation discussion), stop: "Run /retro at the end of a working session, not in a fresh one. The retro needs session context to evaluate zforge's performance."
mkdir -p docs/{feature_name}/.zforge-retro
Run the retro
Invoke the zforge:retro skill. The skill owns the scope boundary, NOT-DO rules, data sources, scoring rubric, finding quality gate, and output format — this command does not duplicate them.
Apply the skill to feature $1 and write its output to docs/{feature_name}/.zforge-retro/{session_id}.md.
Report
Present a brief summary to the user:
- Overall score
- Any findings worth acting on
- If findings suggest plugin changes, mention they can be contributed as PRs to the zforge repo
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 · 35 lines · 9 tokens per session scan A 46f773d5d1a1
retro is a command published in the GitHub repository Langerrr/zforge (10 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 405 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 2026-08-31.
Other commands, from other repositories
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
settings
View or update Shipyard workflow settings.
develop
Implement skill development issues with TDD-governed workflow.
assess
Run an AI literacy assessment — scan the repo for evidence, score three disciplines, produce a timestamped report.
pr-review
Run a comprehensive PR review, post results, then independently assess each finding.
issue-plan-review
Read a GitHub issue and all comments, review the implementation plan, independently assess each finding, and present findings.