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/autonpx skills add doodledood/manifest-dev --skill autogit 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/auto)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/auto"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/auto.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 | $0.00056 | $0.01337 |
| Opus 5 | $0.00028 | $0.00668 |
| Sonnet 5 | $0.00011 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
auto 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chain manifest-dev:figure-out --autonomous (when the transcript lacks shared understanding) → manifest-dev:define --autonomous → manifest-dev:do on a single task. The --autonomous flag on figure-out makes the model self-answer with recommended answers instead of waiting on the user (see figure-out/references/autonomous.md). Surface define's Summary for Approval for visibility, then treat it as approved and proceed to /do.
Task text comes from $ARGUMENTS; if empty, infer from conversation context (summarize the discussed task into a concrete description). Fresh session with no context and no args → halt: No task description provided and no conversation context to infer from. Usage: /auto <task description> | /auto --babysit <pr-url>.
Verification policy. Parse only top-level option uses of --verification and --verifier-model as /auto flags; quoted or topic mentions remain task text. Omitted --verification means per-gate. After resolving that default, load the matching sibling /do reference under ../do/references/ and apply its policy validation before /define; the reference, not /auto, owns mode-specific model support and evidence provenance. Remove parsed flags from the task before /define, and forward them only to /do. Never write either option into the Manifest. Use the reference's required evidence/provenance wording when recording each gate's provenance in the ledger.
Babysit mode (--babysit <pr-url>) skips fresh synthesis. Invoke manifest-dev:define with --babysit <pr-url> --autonomous, then /do with the parsed verification options. PR-lifecycle platform auto-detects from PR URL host (github.com → github composition); non-github host → halt. Multi-repo manifest produced by /define → single /do invocation navigates all repos.
Failure handling. /define returns no manifest path → stop, report. /do escalates (BLOCKED criterion or other blocker) → surface the escalation verbatim to the user with the action it requests.
Unattended launch. At the start of a standalone run, before chaining, establish a durable full-chain goal-setting backstop. Its completion contract spans the whole chain, so continuation does not stop after the first phase. The terminal success condition is outcome-gated: the Manifest is written, /do reports /done, and every Acceptance Criterion and Global Invariant has fresh PASS evidence under the selected verification mode in a manifest gate ledger. /auto owns this backstop as the chain entrypoint: figure-out --autonomous suppresses its standalone Read-level backstop because this parent carries the Read bar as a phase checkpoint before /define, /define only emits the manifest handoff, and /do operates under the existing full-chain contract instead of setting or printing a narrower manifest-only goal. Emit the blocks below verbatim. Do not summarize, shorten, reword, or re-punctuate them. Set it through the harness's goal-setting, continuation, or durable-completion-condition capability where one exists; print it in copy-pasteable form for the user's own continuation mechanism where none does. Emit the chain prefix, then the goal block, then the gate-ledger clause, as one contract: one unlabeled block introduced by a sentence of your own, since the fences and their labels are this file's markers rather than part of what you emit.
Reach shared understanding of the task, then write a Manifest from it. Where an investigation phase runs, complete a full-anatomy Read checkpoint before the Manifest is written: every load-bearing branch pressed; Evidence Ledger explicit; assumptions separated from verified and inferred claims; independent re-derivation run or explicitly unavailable; rival set no longer moving; confidence, evidence, and overturn conditions stated. For diagnosis-shaped work, the Read checkpoint is not complete if it only localizes where the symptom concentrates: name the concrete mechanism — the variable, difference, or sequence that produces the symptom, including why this case differs when the question is comparative — or earn an underdetermined Read by naming the surviving explanations and showing which feasible probes that could distinguish them were run, what they showed, or why they were blocked. Treat a missing or weak Read checkpoint as a phase defect to repair before the Manifest is written, not a post-hoc terminal failure after execution has fresh all-gate PASS evidence. Stop if the run stalls — consecutive turns moving neither the work nor its verification.
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 · 37 lines · 56 tokens per session scan A c48a5e8b4193
auto is a skill published in the GitHub repository doodledood/manifest-dev (72 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 1,337 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…