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 instructions/robzilla1738/codex-workflows/agents-mdgit clone --depth 1 https://github.com/robzilla1738/Codex-WorkflowsWhat 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 | $0.00524 | $0.00524 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
Codex-Workflows AGENTS.md 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- Codex-Workflows CLAUDE.md — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
This repo builds a Codex plugin, not a one-off demo. Treat generated artifacts, plugin metadata, and install docs as part of the product.
Project shape
- Source packages live under
packages/. - Built-in workflow templates live under
workflows/. - The installed plugin bundle is generated under
plugins/codex-workflows/. - Codex skill instructions live under
skills/codex-workflows/SKILL.md. - The repo marketplace is
.agents/plugins/marketplace.json.
Do not edit plugins/codex-workflows/dist/* directly. Change source files,
then run pnpm validate:plugin.
Commands
Use these before handing work back:
pnpm typecheck
pnpm test
pnpm validate:plugin
For a fast workflow smoke:
node plugins/codex-workflows/dist/cli.js validate workflows/bug-sweep.workflow.js --cwd /tmp
node plugins/codex-workflows/dist/cli.js run workflows/bug-sweep.workflow.js --cwd /tmp --adapter simulate --no-watch
For MCP smoke testing, start the generated server from
plugins/codex-workflows and call workflow_validate.
Distribution rules
- Keep install docs pointed at
robzilla1738/Codex-Workflows. - Keep plugin names stable: marketplace
codex-workflows, plugincodex-workflows. - Keep the plugin bundle self-contained. Users should not need to run
pnpmafter installing from GitHub. - Do not leave
/Users/...paths, local cache paths, or machine-specific binaries in the plugin bundle. - If package versions change, regenerate the plugin and commit the generated bundle.
Runtime rules
- Workflow scripts are declarative. They define phases and worker prompts.
- Workflow scripts must not get direct filesystem, shell, network, process, or Node built-in access.
- Bug-finding workflows should default to read-only workers.
- Model overrides from the caller beat workflow defaults.
- Default durable run state belongs under Codex home so read-only runs do not
dirty target repos. Project-local
.codex-workflows/runs/<run-id>/is opt-in and legacy-readable.
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.
- 2d ago First seen · 65 lines · 524 tokens per session scan A 28f9d5a3ec7e
Codex-Workflows AGENTS.md is an instructions file published in the GitHub repository robzilla1738/Codex-Workflows (63 stars, last pushed 2mo ago), licensed MIT. It adds 524 tokens to every session, about $0.0026 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 instructions, from other repositories
opencode-ensemble AGENTS.md
AGENTS.md instructions for hueyexe/opencode-ensemble, covering opencode-ensemble — agent guidelines, what this is, design context, users and brand personality.
tarocub CLAUDE.md
Instructions for cloveric/tarocub, covering tarocub instructions, read first, mission, release rule and persistence rule.
cool-workflow AGENTS.md
AGENTS.md instructions for coo1white/cool-workflow, covering cool workflow — autonomous development agent, quick index, role, hard rule — never push directly to main and iteration loop.
LifeHack-2026 AGENTS.md
Instructions for Ducksss/LifeHack-2026, covering woven agent instructions, canonical context, current snapshot, product and trust invariants and architecture and scope.
LifeHack-2026 CLAUDE.md
Instructions for Ducksss/LifeHack-2026: Before changing this repository, read AGENTS.md in full and follow its canonical context order, product invariants, worktree rules, and definition of done. Then read docs/HANDOVER.md for the latest product and repository state.
LifeHack-2026 copilot-instructions.md
Instructions for Ducksss/LifeHack-2026: Read and follow /AGENTS.md before suggesting or applying changes. It is the canonical source for context order, product and trust invariants, repository hygiene, documentation ownership, and the definition of done.