Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cam-douglas/agent-instructionsnpx agentmods add skills/cam-douglas/agent-instructions/launch-pipelineWrote 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/skills/cam-douglas/agent-instructions/launch-pipeline)<a href="https://agentmods.dev/skills/cam-douglas/agent-instructions/launch-pipeline"><img src="https://agentmods.dev/badge/skills/cam-douglas/agent-instructions/launch-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cam-douglas/agent-instructions/launch-pipeline"><img src="https://agentmods.dev/badge/skills/cam-douglas/agent-instructions/launch-pipeline.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.01271 |
| Opus 5.5 | $0.00016 | $0.00508 |
| Sonnet 5 | $0.00008 | $0.00254 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
launch-pipeline 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch Pipeline
Explicit activation
Use only when the user explicitly invokes /launch-pipeline or asks to run that named lifecycle. A natural-language request for planning, strategy, implementation, or resume does not implicitly activate this skill. Those requests use the repository router and proportionate task guidance.
Required context
Reuse repository-root AGENTS.md and .cursor/AGENTS.md already in context; read missing applicable instructions once. Read .cursor/instructions/LAUNCH.md, then only the instruction sections, source, plans, skills, and evidence selected by its current mode. The parent owns routing and shared state. Bounded delegates receive task packets rather than repeating launch startup or scanning shared state/history.
Preflight and materialization
When a permitted execution tool is available, run from the repository root:
node .cursor/skills/launch-pipeline/scripts/preflight.mjs
Ask Mode may lack execution tools. Then inspect available files, mark preflight not run, and defer execution to a capable mode before mutation. Never bypass the host mode or claim a verified READY status without evidence. Ask and Plan Mode remain read-only.
READY: continue the selected mode; do not bootstrap again because a session started.MATERIALIZATION_REQUIRED: include missing artifacts in the plan. After Build or existing explicit implementation authorization, read.cursor/BOOTSTRAP.md, runbash .cursor/scripts/bootstrap.sh, and require success before dependent work.BLOCKED: preserve evidence and resolve the reported defect within authorization; do not bypass policy.- Explicit installation or repair may also justify bootstrap. Preserve existing hook paths and implementations; newly seeded hook files are not proof of activation.
Procedure
- Inspect preflight or record its execution limitation; infer intake from the user request and relevant repository evidence.
- Select new idea, major change, resume, remediation, or closure under
.cursor/instructions/LAUNCH.md. - Ask only for a strict blocker or consequential owner decision lacking a defensible default, using an available question tool or the conversation. Existing implementation authorization remains valid.
- Present one concise activation summary: mode, preflight, objective, risk/reasons, matched instructions, expected artifacts, any required roles/gates, materialization need, owner decisions, and next action.
- In Plan Mode, present a reviewable plan and wait for Build unless implementation is already explicitly authorized in the current execution mode. Do not introduce a second approval solely because this skill is active.
- Materialize missing setup only when needed, then create the applicable blueprint/phase plan and formal workstream records when that pipeline is active.
- One parent invokes independent workers directly through the host's available delegation tool. Bounded scouts need task packets; formal roles preserve charter, plan, evidence, handoff, required/skipped-role records, and supported verdicts.
- Verify integrated work; route failed formal gates to their owners and require appropriate re-verification. Update materially changed state and existing plans; continue until completion, a strict blocker, or an actual required owner decision.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 104 lines · 40 tokens per session scan A ba6bce9b0d00
launch-pipeline is a skill published in the GitHub repository cam-douglas/agent-instructions (2 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 1,271 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…