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/handoffnpx skills add doodledood/manifest-dev --skill handoffgit 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/handoff)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/handoff"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/handoff.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 | $0.00064 | $0.00507 |
| Opus 5 | $0.00032 | $0.00253 |
| Sonnet 5 | $0.00013 | $0.00101 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
handoff 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 today.
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
Produce a self-contained context payload that lets a fresh agent continue this work without re-deriving or re-learning what this session already established. The argument is what the next session is for — use it to shape what's captured and what's left out.
Capture what's hard-won — anything the new session would have to re-do otherwise. For each item that travels, carry the grounding with it, so the receiver inherits the working state rather than just the conclusion. Examples (illustrative, not required): a settled decision travels with the alternatives considered and why this won; a verified fact travels with how it was verified (file:line, command output, doc URL); an open thread travels with what would close it. If a particular handoff isn't structured around decisions, facts, or threads, capture whatever the goal requires — with its grounding.
Reference other artifacts (PRDs, manifests, ADRs, issues, PRs, commits, diffs) by path or URL — don't restate their content.
Name the skills the next agent should invoke when the work ahead maps to them — the receiver may not know the toolbox it's inheriting.
Redact credentials, tokens, and personal data — the payload outlives this session and may become another agent's prompt verbatim. Point at where a secret lives (an env var name, a vault path) instead of its value.
Shape is the agent's call. Section names, headings, prose-vs-lists, ordering — driven by the intent, not a template.
Output to ~/.manifest-dev/handoffs/handoff-{timestamp}.md (create the dir; ~ = $HOME / %USERPROFILE%) where {timestamp} is YYYYMMDD-HHMMSS in UTC — a durable home so handoffs survive OS temp cleanup between sessions. Fall back to a writable temp path only when the home directory isn't writable. If the argument is a path to a prior handoff, read it first and write a fresh doc reflecting the current state — pure rewrite, not append.
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.
- today Changed · -1 tokens per session c851a0590756
- 5d ago First seen · 21 lines · 65 tokens per session scan A b0c1fd19193d
handoff is a skill published in the GitHub repository doodledood/manifest-dev (72 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 507 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
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…
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.
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.
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).
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.