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 skills add doodledood/manifest-dev --skill manifest-to-goalgit 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/manifest-to-goal)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/manifest-to-goal"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/manifest-to-goal/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/skills/doodledood/manifest-dev/manifest-to-goal"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/manifest-to-goal.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 | $0.00045 | $0.00549 |
| Opus 5.5 | $0.00018 | $0.00220 |
| Sonnet 5.5 | $0.00009 | $0.00110 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
manifest-to-goal 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 11d 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
Turn the supplied Manifest — the specification of what to deliver, what counts as done, and the constraints that hold throughout — into a standalone definition of done. Before drafting, invoke the prompt-engineering skill and apply its principles.
Read the whole Manifest and references needed to understand its intent and requirements. Use the Manifest identified in the request or conversation; ask which one if the target is missing or ambiguous. Apply explicit user amendments, distinguishing settled decisions from suggestions still under discussion. Ask a focused question only when an unresolved choice or contradiction would materially change the goal.
Write for an agent that will have neither the Manifest nor this conversation. Build upward from the finished outcome, adding the conditions that make it acceptable: deliverables, scope, consequential thresholds, quality bar, and delivery or authorization limits. Preserve source-grounded purpose and rationale that guide interpretation or trade-offs, and examples that define a meaningful boundary. Keep assumptions qualified. A retained detail must not revive a superseded goal.
Leave execution strategy to the agent, preserving methods only where they are binding requirements. Omit advisory implementation steps, derivable detail and repeated explanations that add no decision-relevant information. Synthesize related requirements without weakening their conditions. Use plain language in place of gate IDs and workflow jargon; inline essential requirements rather than sending the reader to the Manifest or another requirements document.
Make the successful end state and its proof explicit: carry the specified checks and pass conditions, including qualitative criteria, and require observed results to support completion. Concrete check commands and target artifact names may define success. Preserve supplied stopping limits and approval boundaries without inventing metrics, budgets, reporting formats or extra review gates.
Include execution policy only when specified by the source or user; omit policy already supplied by the known destination. Express retained behavior without depending on a Manifest-specific workflow. A generic execution contract is not required.
Check the draft against the complete source for lost obligations, invented requirements and conflicting scope. If fitting the goal would require a material scope decision, ask rather than conceal an omission.
Return one paragraph inside a single plain-text code fence, with no surrounding commentary. Count the goal text inside the fence programmatically, including spaces and punctuation, and revise until it is at most 4,000 characters; the ceiling is not a target. This invocation drafts text only: it does not edit the Manifest, set a running goal or begin the work it describes.
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.
- 11d ago Changed · +2 lines · +4 tokens per session a9fcbe13e4e6
- 12d ago First seen · 21 lines · 41 tokens per session scan A e945b9bd621a
manifest-to-goal is a skill published in the GitHub repository doodledood/manifest-dev (75 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 549 once invoked, about $0.0002 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 2026-10-05.
Other skills, from other repositories
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
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…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
product-economics
Does this product make money at a price someone will pay? Forces contribution margin, a price with a stated basis, and a bottom-up market size — each number labelled measured / assumed / unknown, so a guess can never be read as a calculation.
cost-model
Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.