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/walidboulanouar/define-doneWrote 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/walidboulanouar/define-done/verify-done)<a href="https://agentmods.dev/commands/walidboulanouar/define-done/verify-done"><img src="https://agentmods.dev/badge/commands/walidboulanouar/define-done/verify-done/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/walidboulanouar/define-done/verify-done"><img src="https://agentmods.dev/badge/commands/walidboulanouar/define-done/verify-done.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 | $0.00022 | $0.00769 |
| Opus 5.5 | $0.00009 | $0.00308 |
| Sonnet 5.5 | $0.00004 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
verify-done 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/verify-done
The 5pm hard stop ritual. Run it once per day, at 5pm, before closing the laptop.
What it does
- Loads the most recent tracker from
008_Builds/define-done/ - Asks the user what shipped today (one outcome at a time)
- Updates the HTML state (preserves the live JS, but writes the truth)
- Logs the day to
008_Builds/define-done/log.md - If today < 3/3 → asks why one specific outcome slipped (not generic "what happened")
- Prompts user to write tomorrow's 3 outcomes BEFORE closing the laptop
- Optionally appends tomorrow's outcomes to the same tracker
Workflow
Step 1 — Load today's tracker
Find the latest file in 008_Builds/define-done/ matching *-define-done.html. Parse the day cards. Find today's day card.
Step 2 — Verify each outcome
Walk through today's 3 outcomes one at a time. For each:
"Outcome 1: {{outcome_text}}. Did it ship? (y / n / partial)"
If n or partial → one follow-up:
"What got in the way? One sentence. We're logging it, not analyzing it."
Record the answer verbatim. Do not editorialize. Do not say "no worries, tomorrow's a new day."
Step 3 — Update the HTML
Edit the today card in the HTML:
- Add
checkedattribute to checkboxes for shipped outcomes - Update the
<span class="score">to the final count (3/3, 2/3, etc.) - Add a
data-verified="true"attribute to the day card
Step 4 — Log the day
Append to 008_Builds/define-done/log.md:
## {{YYYY-MM-DD}} · {{Day name}}
- [x/✗] outcome 1: {{text}}{{ · slipped because: ... if partial/no}}
- [x/✗] outcome 2: {{text}}
- [x/✗] outcome 3: {{text}}
Score: {{hit}}/3 · Closed at: {{time}}
Step 5 — Define tomorrow
"Three outcomes for tomorrow. One sentence each. Verb-first. Done before you close the laptop."
Audit each against the 6 rules from /define-done. Reject vague outcomes. Push back once, then accept.
Add tomorrow's outcomes as a new day card in the same tracker HTML (or roll over to a fresh weekly tracker if Sunday).
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 · 92 lines · 22 tokens per session scan A 6f8f7a95b936
verify-done is a command published in the GitHub repository walidboulanouar/define-done (10 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 769 once invoked, about $0.0001 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
save-prompt
Generalize the current discussion into a reusable prompt and save it as a file.
review-resume
Comprehensive PM resume review against 10 best practices — structure, impact metrics, keywords, and actionable feedback.
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.
generate-report
Generate a professional HTML report from assessment results in the conversation.
release
Generate changelog, bump version, and create git tag.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.