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 commands/kouroshez/coding-os/retrogit clone --depth 1 https://github.com/kouroshez/coding-osWhat 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 | $0.00000 | $0.00656 |
| Opus 5 | $0.00000 | $0.00328 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00066 |
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 yesterday.
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
Run a Scrumban retrospective for the period specified by $ARGUMENTS (default: 14 days).
Steps:
- Resolve period: if
$ARGUMENTSis a number → days; if$ARGUMENTSisweek|month|quarter→ 7|30|90 days; if empty → 14 days. - Call MCP tool
cos_task_retro(since="Nd")(canonical aggregation of completed + blocked + failure patterns;sinceis a duration string like "14d"). - Call
cos_failure_pattern_query(limit=20)to surface recurring failure modes (frequency-rankedroot_causecategories frombacktrack_events; treat count ≥ 2 as recurring — filter client-side). - Call
cos_metric_trend(metric="time_to_solution", window_days=N)to detect process drift. - Read
$COS_PANEL_DIR/.clear1-bypass-log(if present): each line is a self-issuedCLEAR 1enforcement-bypass plus its justification. Report the count + justifications — a rising count means the discipline is being routed around, not internalized. - Promotion candidates: call
cos_learn_suggest(limit=20)and filter client-side to Trusted, not yet promoted lessons (confidence ≥ 0.7 AND times_validated ≥ 3; suggest already excludes promoted rows). For each candidate propose a destination (an existing rule file section, or a skill) and show the draft fromcos_promote(pattern_id, target)— apply NOTHING without explicit user approval. On approval, write the returned content to the agreed destination (governance edit — needs the task marker); the tool already stampedpromoted_to, which removes the row from digest/suggest. - Render in the template below. The action items are the only place the agent should propose content beyond the data — every line needs an owner placeholder + due-date placeholder (the user fills them in).
Template:
## Retro — YYYY-MM-DD (period: {N} days)
### What shipped ({count})
- [TASK-NNN] {title} → complete, {date}
### What broke / blocked ({count})
- [TASK-NNN] {title} — blocked for {days}; root cause: {category}
### Patterns (from cos_failure_pattern_query)
- {recurring category}: {N occurrences}; suggested mitigation: {action}
### Trend (time_to_solution)
- median {Nm} (vs {Nm} previous period) — {improving | stable | regressing}
### Self-issued CLEAR-1 bypasses ({count})
- {justification} — what discipline was skipped, and was it warranted
### Promotion candidates (Trusted lessons → durable rules; {count})
- [#{pattern_id}] {lesson one-liner} — validated {N}×; proposed destination: {rule/skill path} — approve?
### Action items
- [ ] {action} — @owner — due YYYY-MM-DD
No-blame rule (per incident-response): describe the failing system, never the person.
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.
- yesterday First seen · 39 lines · 0 tokens per session scan A 8250cdd37b99
retro is a command published in the GitHub repository kouroshez/coding-os (6 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 656 tokens. 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
create-issue
Create a GitHub issue from the repo's templates, with the right type and labels.
wh:triage
Use when the user wants to triage GitHub issues against Wheeler research plans in .plans/.
wh:dev-feedback
Use when the user wants to file a Wheeler bug or usability issue as a GitHub issue about Wheeler itself.
gsd:capture
Capture ideas, tasks, notes, and seeds to their destination.
template
Manage issue templates for streamlined issue creation.
project-recap
Generate a visual project recap for context switching.