What is preflight-orchestrator?

A pipeline coordinator for eight software-quality gates, running them in a fixed order from linting and tests through packaging and a GitHub pull request.

Use it to initialize and track the preflight pipeline, run each gate only after its prerequisites pass, and manage the full path to shipping.

It stops the process when a check fails, so later stages do not rely on code that has not passed earlier checks.

preflight-orchestrator — Agent for Claude Code by dansasser

Install

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.

Clone the repo

git clone --depth 1 https://github.com/dansasser/claude-code-marketplace

agentmods

npx agentmods add agents/dansasser/claude-code-marketplace/preflight-orchestrator

Made for: Claude Code.

Or install preflight, the plugin that ships this one along with the rest of its 2 skills, 8 commands, 11 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/preflight-orchestrator.svg)](https://agentmods.dev/agents/dansasser/claude-code-marketplace/preflight-orchestrator)

Your own site

<a href="https://agentmods.dev/agents/dansasser/claude-code-marketplace/preflight-orchestrator"><img src="https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/preflight-orchestrator.svg" alt="Measured on agentmods" height="20"></a>

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 743 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00043	$0.00743
Opus 5	$0.00022	$0.00371
Sonnet 5	$0.00009	$0.00149
Haiku 4.5	$0.00004	$0.00074

Measured 7d ago against content hash 4997355fe168, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

preflight-orchestrator 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 7d 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.

plugins/preflight/agents/preflight-orchestrator.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Preflight pipeline orchestrator. Your job is to run quality gates in sequence and enforce that no gate is skipped.

Cardinal Rules

NEVER skip gates - Each gate must explicitly PASS before the next runs
NEVER proceed on failure - Any gate failure stops the pipeline
NEVER allow gate 8 without gates 1-7 passing - Verify state before shipping

Gate Sequence

Gate 1: lint-test     -> Gate 2: coverage      -> Gate 3: cross-platform
Gate 4: python-matrix -> Gate 5: security      -> Gate 6: api-compat
Gate 7: packaging     -> Gate 8: github-pr

Process

Initialize pipeline if not already running:

python .claude/skills/state-management/scripts/init_pipeline.py

For each gate in sequence: a. Check prerequisites:
```
python .claude/skills/state-management/scripts/check_prerequisites.py <gate>
```
b. If prerequisites NOT met, STOP and report blocking gates c. Mark gate as RUNNING:
```
python .claude/skills/state-management/scripts/write_state.py <gate> RUNNING
```
d. Invoke the gate's agent to perform checks e. Update state with result:
```
python .claude/skills/state-management/scripts/write_state.py <gate> PASS|FAIL --details '<json>'
```
f. If FAIL, stop pipeline and report failure context g. If PASS, proceed to next gate
After all gates pass, report success

Gate Agents

Invoke these agents for each gate:

Gate 1: lint-test agent
Gate 2: coverage agent
Gate 3: cross-platform agent
Gate 4: python-matrix agent
Gate 5: security agent
Gate 6: api-compat agent
Gate 7: packaging agent
Gate 8: github-pr agent

Response Format

After each gate:

GATE: [name]
STATUS: [PASS/FAIL]
DURATION: [seconds]
DETAILS: [summary]
NEXT: [next gate or STOP]

On Complete Success

PIPELINE COMPLETE

All 8 gates passed:
  1. lint-test:      PASS (45s)
  2. coverage:       PASS (32s)
  3. cross-platform: PASS (89s)
  4. python-matrix:  PASS (156s)
  5. security:       PASS (23s)
  6. api-compat:     PASS (18s)
  7. packaging:      PASS (67s)
  8. github-pr:      PASS (12s)

Total time: 442s
Ready to ship!

Read the full file on GitHub · 106 lines

Changes

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.

7d ago First seen · 106 lines · 43 tokens per session scan A 4997355fe168

Subscribe to this mod's changes

preflight-orchestrator is an agent published in the GitHub repository dansasser/claude-code-marketplace (9 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 743 once invoked, about $0.0002 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.

CI and CD DevOps and cloud Testing

gate

Builds CI gates that enforce API quality before changes merge — Spectral lint rules, breaking change detection, and governance tooling for OpenAPI/GraphQL/protobuf. Use when designing API lint rulesets, integrating quality gates into CI, or auditing API governance gaps. Trigger with "design API lint rules", "add API…

jeremylongshore/tons-of-skills-marketplace · 71 tokens

CI Accessibility

CI/CD accessibility agent. Conversational agent for setting up, managing, and troubleshooting accessibility CI pipelines. Supports baseline management (fail only on regressions), SARIF output for GitHub code scanning, PR annotations, and threshold configuration. Works with GitHub Actions, Azure DevOps, GitLab CI…

Community-Access/accessibility-agents · 69 tokens

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases.

rjmurillo/ai-agents · 46 tokens

test-pipeline-agent

Test pipeline configuration specialist. Configures PHPUnit, code coverage, test suites, and CI test integration for PHP projects.

dykyi-roman/awesome-claude-code · 28 tokens

hydra-runner

🟢 Hydra's execution head — fast test runner, build executor, and validation agent. Use proactively whenever Claude needs to run tests, execute builds, check linting, verify formatting, run type checks, check git status, execute simple scripts, or validate that changes work. Runs on the cheap tier for speed — ideal…

AR6420/Hail_Hydra · 105 tokens

qa-architect

Reviews test strategy, pyramid distribution, coverage quality, CI gating, and test-environment fidelity.

davistroy/claude-marketplace · 23 tokens