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/cloudbees-oss/devops-agent-kit/flag-rolloutnpx skills add cloudbees-oss/devops-agent-kit --skill flag-rolloutgit clone --depth 1 https://github.com/cloudbees-oss/devops-agent-kitWhat 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 | $0.00025 | $0.00558 |
| Opus 5 | $0.00013 | $0.00279 |
| Sonnet 5 | $0.00005 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
flag-rollout 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flag Rollout: $ARGUMENTS
Parse the arguments to determine action and target.
Action: list (default if no flag name given)
-
flags_applications_list— find all flag applications -
For each application:
flags_list— list all flags -
flags_environments_list— list all environments -
For each environment:
flags_configurations_list— get flag states -
Present a flag inventory:
Feature Flags — [Application Name]
Flag Type Production Staging Default Value name Bool ON/OFF ON/OFF value
Action: status [flag-name]
flags_applications_listthenflags_get_by_name— find the flagflags_environments_list— list environmentsflags_configurations_list— get configuration per environment- Present detailed flag status:
- Flag name, type, description, labels
- State in each environment (enabled/disabled, default value)
- Whether the flag is permanent or temporary
Action: enable [flag-name] [environment]
- Find the flag using
flags_get_by_name - Find the environment using
flags_environments_list - Show current state and what will change
- Ask for confirmation — "Enable [flag] in [environment]?"
flags_configuration_state_update(enabled=true)— enable the flag- Confirm the change
- Offer to post the change to Slack
Action: disable [flag-name] [environment]
Same as enable, but with flags_configuration_state_update(enabled=false)
Action: create [flag-name]
flags_applications_list— find the target application- Ask the user for: flag type (Boolean/String/Number), description, labels
flags_add— create the flag- Confirm creation with flag ID
- Offer to enable it in an environment
Safety guardrails for flag changes:
- Always show current state before any change
- Always ask for confirmation before enable/disable
- After any change, verify the new state with
flags_configurations_list - If changing production flags, add an extra warning: "This will affect production traffic. Confirm?"
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 · 65 lines · 25 tokens per session scan A 2b7294db46bf
flag-rollout is a skill published in the GitHub repository cloudbees-oss/devops-agent-kit (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 558 once invoked, about $0.0001 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…