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/verifygit 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 | $0.00387 |
| Opus 5 | $0.00000 | $0.00193 |
| Sonnet 5 | $0.00000 | $0.00077 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
verify 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 the matrix-targeted verification commands for files that have changed in the current task.
Per ../rules/test-discipline.md: never pytest tests/ -q mid-task (6 min full sweep). Only run the matrix command(s) tied to changed files.
Steps:
- Determine the change scope:
- If
$ARGUMENTSis provided (file paths), use them. - Otherwise run
git diff --name-only+git status --porcelainto gather changed files.
- If
- Map each changed path to its matrix row (from AGENTS.md §Verification Matrix). Surface conflicts: if a file matches no row, ask the user before guessing.
- Build the deduped list of commands to run.
- State the plan: "I will run: ". Show it before executing — gives the user a chance to redirect.
- Run each command. Stream output. Stop at first FAIL with the failing line surfaced.
- On success: append a short work-log note via
cos_work_log_append(task_id=<current>, summary=<one line>). - On failure: do NOT mark the task
complete. Suggest: keep intesting, fix the failure, re-run.
When a full sweep IS allowed (state it out loud first — per test-discipline.md):
- Pre-merge final gate.
- Cross-cutting refactor touching ≥3 matrix rows.
- User explicitly asked "run all tests".
Output format:
## Verification — {N} command(s)
### Plan
- {file pattern} → `{command}`
### Results
- ✅ `{command}` — {duration}
- ❌ `{command}` — {failure summary}, see {line}
### Next step
{recommendation}
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 · 35 lines · 0 tokens per session scan A 16d9a2a0dc8d
verify 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 387 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
export
Export a knowledge abstract to an Obsidian vault — a folder of Markdown notes linked by [[wikilinks]].
info
Display information and statistics about a knowledge abstract.
wh:llmsr-transfer
Use when the user wants to test whether an LLM-SR discovered equation's FORM generalizes to a recording the search never scored, and ingest both transfer numbers into the Wheeler knowledge graph.
wh:resume
Use when starting a new session and restoring Wheeler context from STATE.md or .plans/.continue-here.md.
maestro-next
Unified entry for all development intents — classify intent, assess complexity, route to the correct execution channel: /maestro-companion (lightweight), standard single run, or /maestro and /maestro-ralph (multi-step manual/orchestrated). Pure router, never runs execution loops itself.
analyze-task
Parse user task description -> detect required capabilities -> build dependency graph -> design dynamic roles with role-spec metadata. Outputs structured task-analysis.json with frontmatter fields for role-spec generation.