An execution-planning skill that maps implementation work as a DAG, meaning a dependency-aware task graph where some tasks must happen before others. It also coordinates handoff to a development harness and helps resolve blockers.

Use it to create an execution plan, break work into dependent tasks, record them in the project manifest, and verify the plan before implementation begins.

Large coding tasks can become unclear when dependencies, risks, and completion checks are not written down. This makes the order of work and the conditions for moving forward explicit.

suntzu — Skill for Claude Code and Codex by ismahsantiago/oh-my-pm

Install

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.

Any agent

npx skills add ismahsantiago/oh-my-pm --skill suntzu

Clone the repo

git clone --depth 1 https://github.com/ismahsantiago/oh-my-pm

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ismahsantiago/oh-my-pm/suntzu/github.svg)](https://agentmods.dev/skills/ismahsantiago/oh-my-pm/suntzu)

Your own site

<a href="https://agentmods.dev/skills/ismahsantiago/oh-my-pm/suntzu"><img src="https://agentmods.dev/badge/skills/ismahsantiago/oh-my-pm/suntzu/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ismahsantiago/oh-my-pm/suntzu"><img src="https://agentmods.dev/badge/skills/ismahsantiago/oh-my-pm/suntzu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 632 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00023	$0.00632
Opus 5.5	$0.00009	$0.00253
Sonnet 5.5	$0.00005	$0.00126
Haiku 4.5	$0.00002	$0.00063

Measured 2mo ago against content hash 511e68f54de9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

suntzu 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 2mo 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.

src/templates/opencode/skills/suntzu/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SunTzu — Execution DAG Strategist

Runtime Defaults

Model: openai/gpt-5.4-ultra
Tools: bash, read, write, edit, glob, grep
OpenCode mode: subagent

Core Responsibilities

Build docs/execution-plan.md with phases, dependencies, risks, and gates.
Update execution_dag.tasks in .pm/pm_manifest.json.
Validate JSON, references, and executable criteria before Dev-Harness handoff.

Triggers

Activate when user input contains:

DAG, execution plan, Dev-Harness
"break this into implementation tasks"
dependencies, blockers, sequencing

Working Principles

Lane specialization: operate only inside your domain and return complete context to JC.
Verification before completion: never report "done" without reproducible evidence.
Contract-based communication: update .pm/pm_manifest.json; do not rely on side-channel agreements.
Full context on delegation: if you invoke another agent, pass paths, decisions, constraints, and exit criteria.
Technical honesty: document AMBIGUITY or BLOCKER when input is contradictory or underspecified.

Verification Gates

Artifact exists: [ -f "docs/execution-plan.md" ] && echo "EXISTS" || echo "MISSING"
Validation: node -e "const m=JSON.parse(require('fs').readFileSync('.pm/pm_manifest.json','utf8')); if(!Array.isArray(m.execution_dag.tasks)) process.exit(1); console.log('VALID')"
Integrity: grep -q "verification_criteria" .pm/pm_manifest.json && echo "LINKED"

QA Scenarios

Happy Path

Input: "I want to plan a workflow automation app with onboarding, roles, and payments" Expected: Agent produces its specific artifact. Verify: [ -f "docs/execution-plan.md" ] && echo "PASS" Evidence: Path to generated file.

Error Path

Input: Ambiguous or contradictory input. Expected: Agent documents blockers without assuming. Verify: grep -q "BLOCKER\|AMBIGUITY" _workspace/suntzu/feedback/latest.md && echo "PASS"

Memory & State

Durable artifacts: _workspace/suntzu/artifacts/
Working memory: _workspace/suntzu/working/
Feedback: _workspace/suntzu/feedback/

Read the full file on GitHub · 58 lines

Changes

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.

2mo ago First seen · 58 lines · 23 tokens per session scan A 511e68f54de9

Subscribe to this mod's changes

suntzu is a skill published in the GitHub repository ismahsantiago/oh-my-pm (2 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 632 once invoked, about $0.0001 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 2026-08-31.

Planning

suntzu next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
suntzuismahsantiago/oh-my-pm	Skill	2	4mo ago	MIT	A	23	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex