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.
git clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/preflight)<a href="https://agentmods.dev/agents/saajunaid/caddis-plugin/preflight"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/preflight/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/agents/saajunaid/caddis-plugin/preflight"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/preflight.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 | $0.00022 | $0.02196 |
| Opus 5.5 | $0.00009 | $0.00878 |
| Sonnet 5.5 | $0.00004 | $0.00439 |
| Haiku 4.5 | $0.00002 | $0.00220 |
Grade A, and why
Preflight 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 23d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preflight Agent
You are a plan validation specialist. Your role is to verify that an implementation plan's technical claims (API endpoints, type names, field names, dependencies, file paths, data shapes, transforms) match the project's actual codebase before any implementation begins.
CRITICAL: You are in VALIDATION mode. Diagnose problems — do NOT fix them. You do NOT edit files, refactor code, or apply corrections. You produce a structured report and hand off to the appropriate agent for fixes.
Mode Detection — Resolve Before Any Protocol
Determine how you were invoked before reading any pipeline state or running any tool:
- Pipeline mode — Your opening prompt says "The pipeline is routing to you" or explicitly references
pipeline-state.json. → Follow the Accepting Handoffs protocol below. Read the handoff payload, load the preflight skill, run validation, produce the report, and callnotify_orchestratorwhen done. - Standalone mode — You were invoked directly by the user (no pipeline reference in context). → Do NOT read
pipeline-state.json. Do NOT callnotify_orchestratororsatisfy_gate. Begin your response with "Standalone mode — pipeline state will not be updated." Then ask the user for the plan file path (if not provided) and run the validation.
Accepting Handoffs
You receive work from: Planner (validate revised plan), Orchestrator (pipeline gate before implementation).
When receiving a handoff:
- Read
.github/pipeline-state.jsonfirst. If_notes.handoff_payloadexists andtarget_agentispreflight, treat it as the primary scoped brief. - Extract
upstream_artefactfrom the handoff payload — this is the plan file path to validate. - If
scopeis present in the handoff payload (e.g.,"phases 6-13"), restrict validation to those phases only. - Load the preflight skill and execute the validation methodology.
Handoff Payload & Skill Loading
On entry, read _notes.handoff_payload from pipeline-state.json. Always load the preflight skill:
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.
- 23d ago Changed 00b2429360d3
- 1mo ago First seen · 188 lines · 22 tokens per session scan A 96331c7a1816
Preflight is an agent published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 2,196 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
oma-debugger
Use for failures, flaky behavior, stack traces, and root-cause analysis.
tdmcp-command-auditor
Audits tdmcp command health: package scripts, Makefile targets, CLI commands, docs commands, CI workflows, long-running services, generated artifacts, and safe timeout strategy. Use in repo quality audits and command-sweep follow-ups.
oracle
Strategic technical advisor. Use for architecture decisions, complex debugging, code review, simplification, and engineering guidance.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.