survey-code

A codebase investigation workflow that examines existing files, patterns, and constraints before planning a change.

In plain words
What is it for?
Use it to explore a repository before writing an implementation plan and identify the files and conventions that matter.
Why use it?
It reduces the risk of planning work that conflicts with the project’s current structure or misses relevant code.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/nirecom/agents/survey-code
Any agent
npx skills add nirecom/agents --skill survey-code
Clone the repo
git clone --depth 1 https://github.com/nirecom/agents

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,169 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.01169
Opus 5 $0.00010 $0.00584
Sonnet 5 $0.00004 $0.00234
Haiku 4.5 $0.00002 $0.00117

Measured yesterday against content hash bc8ee0581f9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

survey-code 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.

skills/survey-code/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Investigate the codebase related to the given task.

Procedure

Step SVC-0 — Resolve <PLANS_DIR>

Before any tool call below that references <PLANS_DIR>, run the following Bash command exactly once:

PLANS_DIR=$(bash "$AGENTS_CONFIG_DIR/bin/workflow-plans-dir" 2>/dev/null \
              || printf '%s\n' "${WORKFLOW_PLANS_DIR:-$HOME/.workflow-plans}")
printf 'PLANS_DIR=%s\n' "$PLANS_DIR"

Capture the printed absolute path and substitute it for every <PLANS_DIR> placeholder in the remainder of this SKILL.md. Subagent prompts must receive the resolved absolute path as a literal string (subagents cannot expand $VAR). Reuse across all subsequent steps in this skill invocation — do not re-resolve.

When invoked as a parallel Agent subagent by workflow-init, the orchestrator passes artifact_path and context_path as resolved absolute strings — use those instead of running Step SVC-0.

Canonical documentation: skills/_shared/resolve-plans-dir.md.

SVC-1. Claim extraction (run before reading any code): Input precedence (read whichever exists first): (a) <PLANS_DIR>/<session-id>-intent.md — preferred (post-clarify-intent calls) (b) <PLANS_DIR>/<session-id>-context.md — fallback (pre-clarify-intent calls from workflow-init; use "User initial prompt" and "Issue body" sections) If neither exists: proceed to Step SVC-2 with an empty claim list. Extract up to 5 behavioral/factual claims from Background/Motivation and Scope. Target: "X is blocked", "X does Y", "X is broken", "X cannot Z". Exclude aesthetic claims and pure preferences. Works with Japanese and English content.

SVC-2. Identify candidate files and areas using Glob and Grep. SVC-3. Read relevant source files, configs, tests, and docs. SVC-4. For each claim extracted in Step SVC-1, verify it against the current codebase:

  • verdict: holds — evidence in code confirms the claim
  • verdict: contradicted — evidence in code contradicts the claim
  • verdict: indeterminate — insufficient evidence to confirm or deny SVC-5. Summarize: existing patterns, architectural constraints, relevant files (with line numbers), and anything that affects implementation. SVC-6. Write findings to <PLANS_DIR>/<session-id>-survey-code.md. The file must include a ## Verified Claims section:
## Verified Claims
- claim: <text from intent.md>
  verdict: holds | contradicted | indeterminate
  evidence: <file:line or "no matching code found">

If no claims were extracted in Step SVC-1, write the section with the note "No verifiable behavioral/factual claims found in intent.md or context.md."

Read the full file on GitHub · 95 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.

  1. yesterday First seen · 95 lines · 20 tokens per session scan A bc8ee0581f9d

Subscribe to this mod's changes

survey-code is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 1,169 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens