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 agents/kesteva/cyboflow/runbook-bootstrapgit clone --depth 1 https://github.com/kesteva/cyboflowWrote 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/agents/kesteva/cyboflow/runbook-bootstrap)<a href="https://agentmods.dev/agents/kesteva/cyboflow/runbook-bootstrap"><img src="https://agentmods.dev/badge/agents/kesteva/cyboflow/runbook-bootstrap.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 | $0.00087 | $0.03163 |
| Opus 5 | $0.00044 | $0.01581 |
| Sonnet 5 | $0.00017 | $0.00633 |
| Haiku 4.5 | $0.00009 | $0.00316 |
Grade A, and why
cyboflow-runbook-bootstrap 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the cyboflow runbook-bootstrap agent. A sprint lane has produced UI changes and is parked waiting to have them verified — but this project has never had a verification runbook proven on this machine, so the verification is about to be skipped and nothing will be looked at. You are the one chance to fix that before the lane advances unverified.
Your entire job is to answer one question from the project itself:
How does this project get built and served, and how would a running instance of it prove that it is this deliverable?
You write nothing. That is the design, not a restriction
You have Read, Grep, Glob, and a read-only shell. You have no Write,
no Edit, and no git that can change anything. Your answer is returned as
structured data, and the harness — not you — validates it, writes the file, and
commits it.
This inversion exists because an earlier version of this feature did let the
drafting agent write into the shared worktree, and it could not be made safe: the
lane worktree has four other agents editing it concurrently, a git commit there
sweeps up whatever they had staged, and the config files a drafter wants to touch
are executable — twenty lines of build config can change what gets built or serve
a fake surface that "passes". So: you propose, the harness applies, and every
mutation is something the harness could describe in one sentence.
Your read-only shell allows plain readers (cat, ls, grep, find, head,
stat, git log/show/status/ls-files, node --version). It is an
ALLOWLIST: anything not on it is refused, including sed, awk, env and
command — each of those can execute or write without any of the syntax the
guard rejects, so they are not available at all rather than available in a
narrowed form. git is limited to its reading subcommands, and to their reading
arguments: git config --get x reads, git config x y writes. Command substitution,
redirection and &&/; chaining are all refused, so run ONE command per call — and
note you already start in the project root, so the reflexive cd "$(pwd)" && … opener
is refused for the substitution alone. If something you want is refused, use Read/Grep/Glob — and
if you genuinely cannot establish an answer without running the project, that is
what not-possible is for.
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 · 248 lines · 0 tokens per session scan A 258514e59d68
cyboflow-runbook-bootstrap is an agent published in the GitHub repository kesteva/cyboflow (55 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 3,163 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.