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/sync-toolsnpx skills add doodledood/manifest-dev --skill sync-toolsgit 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/sync-tools)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/sync-tools"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/sync-tools.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 | $0.00045 | $0.02688 |
| Opus 5 | $0.00023 | $0.01344 |
| Sonnet 5 | $0.00009 | $0.00538 |
| Haiku 4.5 | $0.00005 | $0.00269 |
Grade A, and why
sync-tools 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sync-tools — Multi-CLI Distribution Generator
Generate distribution packages for OpenCode, Codex CLI, and Pi from the Claude Code plugin.
Input: $ARGUMENTS — optional CLI name (opencode, codex, pi) to sync one target. Empty = all targets.
Paths
| Role | Path |
|---|---|
| Sources (read-only) | claude-plugins/manifest-dev/ and claude-plugins/manifest-dev-tools/ |
| Output | dist/{opencode,codex,pi}/ |
| Conversion rules | .claude/skills/sync-tools/references/{cli}-cli.md |
| Per-CLI sync state | dist/{cli}/.sync-meta.json (records last-synced source SHA — drives diff-first workflow) |
| Pi namespace metadata | dist/pi/component-namespaces.json (component → owning plugin; Pi only) |
| GitHub repo | doodledood/manifest-dev |
Scope
Sync only these source payloads:
claude-plugins/manifest-dev/— core workflow skills.claude-plugins/manifest-dev-tools/— tools skills.
Both plugins are skills-only — manifest-dev ships no agents or hooks on any target (the former functional agents are skills).
Never sync other plugins — anything under claude-plugins/ that is not one of the two payloads above, including PLUGIN_TEMPLATE. Never modify source files. Skip sync-tools skill from output (meta-tool). It lives in .claude/skills/, outside both synced payloads, so today this excludes nothing — it is stated deliberately, so that moving it under claude-plugins/ does not silently make the generator distribute itself.
Namespacing model is per-CLI (see each reference file):
- Plugin-native targets (Codex, OpenCode): the plugin is the distribution unit. Codex: two plugins (
manifest-dev,manifest-dev-tools) each bundle their skills under original names. OpenCode: one plugin entry (dist/opencode/plugin/) registers the whole skills payload viaskills.paths; skills keep bare names (native discovery is first-found-wins). No install-time suffixing, nocomponent-namespaces.json, no installer. Plugin-qualified skill-reference handling (manifest-dev:<skill>— strip vs keep) is per-CLI: see each reference file. - Package target (Pi): each component carries plugin ownership in
component-namespaces.json(ownership metadata — Pi keeps package-scoped skill names, no suffixing). Regenerate it on every sync from the discovered source components; never hand-maintain it.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 122 lines · 45 tokens per session scan A 88fa4ca0d7b3
sync-tools is a skill published in the GitHub repository doodledood/manifest-dev (72 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 2,688 once invoked, about $0.0002 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
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
oma-hwp
Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…