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 skills/doodledood/manifest-dev/donenpx skills add doodledood/manifest-dev --skill donegit clone --depth 1 https://github.com/doodledood/manifest-devWrote 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/skills/doodledood/manifest-dev/done)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/done"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/done.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.00445 |
| Opus 5 | $0.00030 | $0.00222 |
| Sonnet 5 | $0.00012 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
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 4d 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
Receive the manifest path, selected verification mode, explicit or inherited verifier-model provenance, gate ledger, and the selected verification reference's evidence/provenance wording from /do.
Emit a completion summary in plain prose: what was built, the key changes (files, behavioral effect — not just paths), any Process Guidance departed from and any deviation from the Initial Approach or the Deliverable order with why, anything notable about how the work landed. State the verification mode, model provenance, and evaluator provenance exactly from the supplied ledger and selected-reference wording. Name any findings a gate reported below its threshold, too — they were handed over rather than repaired, and this summary is where the user meets them — and any gate whose bar the run read as suspect without a user to ask, with what the rounds beneath it turned up. Name all of these even when an execution log already records them; a reader of the summary should not have to open the log to learn which advisory guidance was set aside or how the plan moved. Adapt detail to the task's complexity — a small fix gets a couple of sentences; a multi-deliverable refactor gets a paragraph or two. Multi-repo manifests: a single summary covers the whole manifest, naming which repos' deliverables were verified.
Reachable only after every Acceptance Criterion and Global Invariant has fresh PASS evidence under the selected mode in /do's gate ledger, with no unverified, FAIL, stale, BLOCKED/actionable, or escalation-pending criteria. End with the mandatory trailing line — directive, not observational, because the manifest stays the source of truth post-completion:
If the next message describes a change or new requirement (not a pure question), invoke /manifest-dev:define <this-manifest-path> to amend. Pure questions are answered inline.
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.
- 4d ago First seen · 16 lines · 60 tokens per session scan A 6b64a67692c3
done is a skill published in the GitHub repository doodledood/manifest-dev (72 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 445 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
update-lid
Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…
map-codebase
Bootstrap LID in an existing (brownfield) codebase. Deep-reads every file in the declared scope, offers lens-based clustering options, generates skeleton LLDs/HLD/EARS bottom-up, then creates arrow docs and prompts the user to flesh out the skeletons. Token-intensive by design. Use when asked to map a codebase…
bidirectional-differential
Audit coherence across an arrow of intent by running two parallel fresh Claude sessions — one reconstructs code from a single EARS, the other reconstructs the EARS from stripped code — then classifies the drift between them. Use when the user invokes /differential-audit, asks to audit EARS-to-code drift for a feature…
fix
Разобраться, когда человек говорит «что-то сломалось» или «не работает», и назвать конкретное звено системы, а не человека. Использовать, когда пользователь пишет /fix, жалуется «ничего не происходит», «опять ошибка», «не запускается», или явно не понимает, что пошло не так. По-английски: «it doesn't work», «something…
what
Сказать человеку одной строкой, где он сейчас в работе с системой, и что сделать дальше. Использовать, когда пользователь пишет /what, спрашивает «где я», «что дальше», «что сейчас происходит», «на чём я остановился», говорит «where am I», «what's next», «what is going on», или явно потерял нить работы. Не меню и не…
refresh
Bring this project's Clawness rules up to date with the framework version it actually runs. Establishes what is installed and what the codebase uses, looks up what changed since the rules were verified, and writes version-corrected overrides into .clawness/rules/ — reporting the list and stopping for approval before…