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/0xcozart/apex-workflow/agents-mdgit clone --depth 1 https://github.com/0xCozart/apex-workflowWrote 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/instructions/0xcozart/apex-workflow/agents-md)<a href="https://agentmods.dev/instructions/0xcozart/apex-workflow/agents-md"><img src="https://agentmods.dev/badge/instructions/0xcozart/apex-workflow/agents-md.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 5.1 | $0.00535 | $0.00535 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
apex-workflow 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 5d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apex Workflow Agent Instructions
This repo is an installable workflow harness.
Read docs/CODEBASE_MAP.md for codebase orientation before searching broadly. Read CONTRIBUTING.md before modifying
Apex Workflow itself; it defines shared surfaces, verification expectations, and parallel-agent collision rules for this
repo.
When a user asks you to install or configure Apex Workflow for an app repo, do not stop at copying the skill. Configure the target repo with the harness installer.
Install Flow
- Identify the target app repo path.
- Inspect the target repo enough to choose tracker, GitNexus/code-intelligence, browser, verification, and profile review needs from repo evidence.
- Run the installer with explicit choices:
npm run init -- \
--target=/path/to/app \
--config-mode=custom \
--tracker=linear \
--tracker-team="Team Name" \
--tracker-project="Project Name" \
--code-intelligence=gitnexus-mcp \
--browser=agent-browser \
--origin=http://127.0.0.1:3000 \
--yes
The installer writes apex.workflow.json, creates or updates a managed Apex block in AGENTS.md, validates the
generated profile, and symlinks the local skill into the Codex skills directory unless --skip-skill-link is passed.
After the install report prints, review inferred path confidence, adapter choices, dirty repo state, and baseline
checkpoint guidance. Confirm or correct any setup.inferredPaths entries marked guessed before starting the first
implementation slice.
Discovery is advisory only. Use --discover or apex-profile discover to collect candidate profile fields after
explicit adapter choices are set, not as a replacement for repo-specific configuration judgment.
Guardrails
- Do not overwrite an existing
apex.workflow.jsonunless the user asked for a refresh or you pass--forceintentionally. - Do not add Linear, GitNexus, browser automation, or design gates unless the target repo has them or the user chooses them.
- Do not put human cautions in
authority.doNotUseAsAuthority; useoperatorCautionsfor security, public/private boundary, or secret-handling warnings. - Prefer GitNexus through MCP when the user chooses GitNexus. If MCP fails in the target environment, configure or document a repo-local wrapper fallback.
- App-specific product truth belongs in the target repo profile, not in the generic Apex skill.
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.
- 5d ago First seen · 53 lines · 535 tokens per session scan A 247f8ab58883
apex-workflow AGENTS.md is an instructions file published in the GitHub repository 0xCozart/apex-workflow (1 stars, last pushed 1mo ago), licensed MIT. It adds 535 tokens to every session, about $0.0027 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 2026-08-31.
Other instructions, from other repositories
cezar AGENTS.md
AGENTS.md instructions for open-mercato/cezar, covering agents.md — working in this repository, zero config, changing a mechanism that already works, the http api and repository layout.
vibe-coding-repository-standard AGENTS.md
Instructions for cz1993/vibe-coding-repository-standard, covering vcrs repository instructions, purpose, communication, change discipline and privacy and safety.
codex-pets AGENTS.md
Instructions for astandrik/codex-pets, covering agents.md, commands (verified), workflow, file map and golden samples (follow these patterns).
hop AGENTS.md
Instructions for amittamari/hop, covering agent map, start here, what this repo builds, working rules and common commands.
telltale CLAUDE.md
Claude Code instructions for sanlee-ys/telltale, covering telltale — contributor contract, build and test, golden tests: the actual workflow and its traps, a council test never spawns a vendor and a council test never writes the operator's own state.
TreeWork AGENTS.md
Instructions for Johnny-xuan/TreeWork, covering treework repository guidance, read before editing, repository boundaries and change discipline.