A codebase-mapping pre-flight tool that builds a structural picture of an existing project before changes are made. It shows files, symbols, and how parts of the code connect.

Building or refreshing a code map, looking up symbols, and checking which parts of a project a change may affect.

It helps prevent changes based on a mistaken understanding of how the frontend and backend fit together.

preflight — Skill for Claude Code and Codex by samibs

Install

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.

Any agent

npx skills add samibs/skillfoundry --skill preflight

Clone the repo

git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code, Codex.

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/skills/samibs/skillfoundry/preflight.svg)](https://agentmods.dev/skills/samibs/skillfoundry/preflight)

Your own site

<a href="https://agentmods.dev/skills/samibs/skillfoundry/preflight"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/preflight.svg" alt="Measured on agentmods" height="20"></a>

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 796 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00009	$0.00796
Opus 5	$0.00005	$0.00398
Sonnet 5	$0.00002	$0.00159
Haiku 4.5	$0.00001	$0.00080

Measured 3d ago against content hash d68c849bc8a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 3d 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.

.agents/skills/preflight/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Codebase Comprehension Pre-Flight. You give agents a structural model of existing code BEFORE they write, attacking the framework's #1 failure class — the Frontend-Backend Contract Mismatch. You are backed by the sf_codemap MCP tool (engine: mcp-server/src/agents/codemap/). You are a sibling to the environment pre-flight (agents/_env-preflight-protocol.md): that one inspects the environment, you inspect the code. See agents/_codemap-preflight-protocol.md for the full protocol.

Persona: See agents/preflight.md for full persona definition.

Usage

/preflight (or refresh) → sf_codemap { projectPath, mode: "refresh" } — incremental rebuild (re-parses only changed files).
/preflight build → sf_codemap { mode: "build" } — full rebuild.
/preflight query <symbol> → sf_codemap { mode: "query", symbol } — look up a symbol/file + its edges.
/preflight diff-impact → sf_codemap { mode: "diff-impact" } — blast radius of the working-tree diff.

The map is cached at .skillfoundry/code-map.json (git-ignored by default).

What the Code Map contains

Structure — file / function / method / class / export nodes; contains + same-file calls edges.
Imports — resolved imports edges + unresolvedImports[] (the sf_import_validator baseline).
Contract surface — endpoints[] (method, canonical :param path, handler, best-effort request shape) for Express/Fastify/Hono/Next/NestJS/FastAPI/Flask. The sf_contract_check baseline.
DB/layers — model nodes (Prisma/Drizzle/…); every file tagged db/backend/frontend/shared.

Output format

CODE MAP — <project>
Mode:        refresh (re-parsed N files)
Nodes: <n>   Edges: <e>   Endpoints: <count>   Unresolved imports: <count>
Built from:  <git sha | null>
Warnings:    <list, if any>

For query, print the matched node (kind, file:line, layer) and its in/out edges. For diff-impact, print changed + impacted file counts and the impacted file list.

Read the full file on GitHub · 51 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.

3d ago First seen · 51 lines · 9 tokens per session scan A d68c849bc8a0

Subscribe to this mod's changes

preflight is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 2d ago), licensed MIT. It adds 9 tokens to every session and 796 once invoked, about $0.0000 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 2026-09-03.

Claude Code Debugging Planning ai-agents ai-coding ai-framework code-quality copilot

bug-fix

Guided end-to-end bug-fix workflow for Plan Forge tempering bugs — load → pre-fix review → write failing test → fix → validate → post-fix sweep → close. Composes /code-review, /clean-code-review, /forge-quench, and /test-sweep around the forgebug tool surface so a fix never closes without a regression check.

srnichols/plan-forge · 80 tokens

forge-troubleshoot

Diagnose and resolve Plan Forge issues — failed runs, broken validation gates, misconfigured environments, stalled slices, and orchestrator errors. Use when a plan run fails or the forge behaves unexpectedly.

srnichols/plan-forge · 44 tokens

health-check

Run a full Plan Forge health diagnostic — environment, setup validation, and completeness scan. Use to verify your forge is properly configured and code is clean.

srnichols/plan-forge · 33 tokens

audit-loop

Run a recursive audit drain loop — discover findings from the running system, triage each into bug/spec/classifier lanes, repeat until convergence. USE FOR: end-to-end audit of a deployed or locally-running app, draining findings to zero. DO NOT USE FOR: single-shot tempering runs (use forgetemperingrun), one-off bug…

srnichols/plan-forge · 100 tokens

systemic-issue-triage

Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.

Gentleman-Programming/gentle-ai · 57 tokens

issue-root-resolution

Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.

Gentleman-Programming/gentle-ai · 45 tokens