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 konamgil/mandu --skill mandu-agent-workflowgit clone --depth 1 https://github.com/konamgil/manduWrote 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/konamgil/mandu/mandu-agent-workflow)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-agent-workflow"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-agent-workflow.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00947 |
| Opus 5 | $0.00025 | $0.00474 |
| Sonnet 5 | $0.00010 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
mandu-agent-workflow 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 8d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu Agent Workflow
Mandu is an agent-native fullstack framework. Agents should not begin by guessing file structure or calling low-level tools directly. Start with the official agent surface, then use domain tools only when the plan identifies a specific domain.
When to Use
Use this skill for every Mandu project task that may inspect, create, modify, or verify application code, framework configuration, contracts, slots, islands, or deployment artifacts.
Canonical Workflow
Always follow this loop:
context -> plan -> apply -> verify -> repair
context: read the project map.plan: convert the user request into domains, files, risks, and checks.apply: prefer intent-level MCP/domain tools; direct edits must be grounded in the plan.verify: run the single agent-facing verification report.repair: convert failures into next actions, then verify again.
Preferred MCP Tools
Use these first when MCP is available:
| Step | Tool | Purpose |
|---|---|---|
| context | mandu.agent.context |
Project map, routes, APIs, slots, contracts, guard, diagnostics. |
| plan | mandu.agent.plan |
Deterministic task plan with domains, files, tools, risks. |
| apply | mandu.agent.apply |
Ordered action preview from .mandu/agent-plan.json. |
| verify | mandu.agent.verify |
Unified post-change guard/diagnose/contract report. |
| repair | mandu.agent.repair |
Structured next actions from .mandu/agent-verify.json. |
If MCP is unavailable, use the CLI equivalents:
mandu agent context --json
mandu agent plan "<task>" --json --write
mandu agent apply --from .mandu/agent-plan.json --json
mandu agent verify --changed --json --write
mandu agent repair --from .mandu/agent-verify.json --json
Allowed File Edits
Direct file edits are allowed only after plan identifies the relevant domain
and the agent has inspected the local pattern. Prefer MCP/domain generation for:
- pages, layouts, and API routes
- contracts and OpenAPI-related files
- slots and fillings
- islands, partials, and hydration boundaries
- deploy intent and provider artifacts
What ships with it
1 file 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.
- 8d ago First seen · 125 lines · 50 tokens per session scan A ccdbf0a89e7f
mandu-agent-workflow is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 11d ago), licensed MPL-2.0. It adds 50 tokens to every session and 947 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
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
truecourse-list
List TrueCourse violations found in this repository.
plan
Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.
flash-reel
Generates a 30-second 9 16 cinematic reel from a user prompt (setting + vibe + rough storyline). Flash Reel — 30s Cinematic Reel Skill When to use User provides: a setting, a vibe/mood, and optionally a rough storyline. They want a 30 second 9:16 reel with hard cuts every 3-4 seconds, anchored by one or more…
kling-3-prompt-director
Production-ready Kling 3.0 video prompt director using the canonical 9-field formula. Includes locked character/environment specs for the Crococopter and Swa & Danny universes. Trigger on any request pairing "Kling" with prompt-related verbs.