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 commands/bybren-llc/safe-agentic-workflow/indexgit clone --depth 1 https://github.com/bybren-llc/safe-agentic-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/commands/bybren-llc/safe-agentic-workflow/index)<a href="https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/index"><img src="https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/index.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 | $0.00000 | $0.01533 |
| Opus 5 | $0.00000 | $0.00766 |
| Sonnet 5 | $0.00000 | $0.00307 |
| Haiku 4.5 | $0.00000 | $0.00153 |
Grade A, and why
index 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 yesterday.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commands
Thirty-five commands you invoke by name: 24 on the Claude surface and 11 Gemini-only media commands that have no counterpart anywhere else. Commands are explicit workflows with steps and side effects — unlike skills, which the model chooses for you.
Five commands are deprecated aliases kept alive for muscle memory; they are listed last, and each one names its replacement.
The work session
The bookends of a ticket. /start-work holds a stop-the-line gate — it refuses a ticket with no
acceptance criteria, which is the single most load-bearing behavior in this group.
/start-work— opens a Linear ticket behind the mandatory AC/DoD gate, then branches from the latest dev/check-workflow— traffic-light health check on branch naming, ticket linkage, commit format, rebase status and docs/sync-linear— derives status from branch commits and writes status, labels and a progress comment back to the ticket/end-work— session-close checklist: commit outstanding work, update the ticket, preserve context before a switch/retro— seven-section retrospective of the session, from what worked well through metrics to wins
Getting a change merged
The validation gate and the routes through it. /pre-pr is mandatory; /quick-fix is the
deliberately reduced path for small bugs and says so explicitly.
/pre-pr— the mandatory gate: CI suite, markdown lint, clean tree, rebase onto dev, commit-message format check/quick-fix— fast-track bug fixes with reduced validation, a minimal PR template, and explicit scope limits/update-docs— scans the branch diff for every doc the change touches, enforcing the docs-in-the-same-PR rule/test-pr-docker— labels a PR to trigger a CI image build, then guides pulling and verifying thepr-Nimage/release— the six-phase release: validate, merge PRs, bump version, tag and publish, sync branches, clean up
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.
- yesterday First seen · 124 lines · 0 tokens per session scan A bdf63f4cb3c4
index is a command published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,533 tokens. 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 2026-09-03.
Other commands, from other repositories
implement
Execute all implementation tasks from tasks.md with test-driven development, parallel batching, and atomic commits.
constitution
Add, update, or remove engineering principles in docs/project/engineering-principles.md with atomic versioned commits.
dark-factory-fix-issue
Implement a fix from investigation artifact for the Dark Factory — code changes, Python + Bun deps, light validation, commit (no PR).
generate-commit-message-draft
You are a coding assistant operating at the root of a Git repository. Follow the steps below carefully. If any step fails, continue the process and note the reason in the Notes section at the end of the output.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
智能创建 git 提交，分析代码变更并生成符合项目规范的提交信息.