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/bahayonghang/my-ai-cli-toolkit/codex-dynamic-workflowsnpx skills add bahayonghang/my-ai-cli-toolkit --skill codex-dynamic-workflowsgit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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/bahayonghang/my-ai-cli-toolkit/codex-dynamic-workflows)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/codex-dynamic-workflows"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/codex-dynamic-workflows.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 | $0.00078 | $0.02380 |
| Opus 5 | $0.00039 | $0.01190 |
| Sonnet 5 | $0.00016 | $0.00476 |
| Haiku 4.5 | $0.00008 | $0.00238 |
Grade A, and why
codex-dynamic-workflows 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Dynamic Workflows
Use this skill to decide whether a Codex task needs dynamic workflow orchestration, then safely shape and run that workflow only when the trigger is real. A valid workflow has an explicit success contract, disjoint work packets, an integration policy, and verification matched to risk.
This skill works in agents that support skills. Do not claim that a local script can call subagent tools unless the current environment exposes such a runner. When no programmable runner exists, create a human-readable orchestration artifact, simulate packets locally, and operate only through the available agent tools.
Trigger Boundary
Trigger this skill when the user explicitly asks for one of these ideas:
- swarm, subagents, parallel agents, multi-agent workflow, dynamic workflow, agent orchestration
- 多智能体、多 agent、并行智能体、动态工作流、编排、分包执行
- a coordinated workflow that combines research, implementation, review, and verification across independent packets
Do not trigger this skill for these prompts by themselves:
- ordinary code review or PR review
- planning-only discussion or an implementation plan with no execution orchestration request
- a single-thread bugfix, typo fix, local script edit, or small refactor
- a routine audit or migration where one agent can inspect, edit, and verify directly
- broad words such as “large”, “audit”, or “migration” without a packeted orchestration need
If a prompt names this skill explicitly but the task is too small, say that full orchestration is unnecessary and proceed directly without creating workflow artifacts unless the user asked for durable artifacts.
Decision Rule
Use dynamic orchestration when the explicit trigger is present or at least two independent workflow dimensions are present:
- research or dependency/API investigation
- implementation across disjoint files or modules
- dedicated review, security, risk, or UX packet
- test, QA, migration dry-run, or verification packet
- docs, examples, rollout, or operational handoff packet
- reusable workflow recipe or durable artifact needed for later runs
What ships with it
9 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.
- agents/interface.yaml 350 B
- evals/evals.json 3.2 KB
- references/plan-schema.md 2.3 KB
- references/risk-gates.md 2.4 KB
- references/validation-examples.md 3.5 KB
- scripts/collect_results.py 2.3 KB runs code
- scripts/new_workflow.py 6.4 KB runs code
- scripts/verify_workflow.py 3.1 KB runs code
- tests/workflow-scripts.test.mjs 6.3 KB runs code
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 · 276 lines · 78 tokens per session scan A 22c54cf96bf6
codex-dynamic-workflows is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed 4d ago), licensed MIT. It adds 78 tokens to every session and 2,380 once invoked, about $0.0004 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
repository-manager-parallel-lane-orchestration
Run a program as one central orchestrator plus many parallel worker agents: brief each lane, land its branch into main locally the moment it arrives, prune the branch and worktree immediately, and push only once the program is complete. Covers the lane briefing contract, land-as-they-arrive merge discipline…
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
bump-mthds
Move this repo's exact mthds dependency pin to the latest release on PyPI (or a version you name), re-lock, adapt the engine source to whatever the new release broke, run the checks, and write the CHANGELOG entry — stopping before the commit. Use whenever the user says "bump mthds", "update mthds", "upgrade mthds"…
add-migration
Write a migration ledger entry for a configuration schema change in pipelex, so that a user's existing file can be repaired instead of thrown away. Use when make check-migration-schemas (alias cmig) or make check-ledger (alias cl) refuses a change, when the user says "add a migration", "write the ledger entry", "the…
add-model
Add a new AI model to the Pipelex inference system. Guides through all required steps: backend TOML configuration (OpenAI, Azure, Anthropic, Google, etc.), kit sync, test profile collections, and fixture regeneration. Use when the user says "add a model", "add GPT-X", "add Claude X", "new model", "register a model"…
release
Automates the Pipelex release workflow: bumps the version in pyproject.toml, finalizes the CHANGELOG.md Unreleased section, runs quality checks, creates a release/vX.Y.Z branch, commits, pushes, and opens a PR to main. Use when user says "release", "cut a release", "bump version", "prepare a release", "make a…