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.
npx agentmods add skills/data-system-school/agent-skills/investigate-codebasenpx skills add Data-System-School/agent-skills --skill investigate-codebasegit clone --depth 1 https://github.com/Data-System-School/agent-skillsWrote 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/data-system-school/agent-skills/investigate-codebase)<a href="https://agentmods.dev/skills/data-system-school/agent-skills/investigate-codebase"><img src="https://agentmods.dev/badge/skills/data-system-school/agent-skills/investigate-codebase.svg" alt="Measured on agentmods" 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 | $0.00125 | $0.01961 |
| Opus 5 | $0.00063 | $0.00981 |
| Sonnet 5 | $0.00025 | $0.00392 |
| Haiku 4.5 | $0.00013 | $0.00196 |
Grade A, and why
investigate-codebase 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate Codebase
Objective
Build the minimum sufficient, falsifiable model needed to answer the user's question. Prefer a thin vertical slice over an exhaustive repository summary. Optimize for human understanding and verification, not the amount of code read.
Operating contract
- Read all applicable repository and agent instruction files before inspecting
implementation, including nested per-directory files under whichever convention
the repository uses (for example
AGENTS.md,CLAUDE.md, orCONTRIBUTING.md). - Default to read-only investigation. Do not edit files, install dependencies, switch branches, reset state, or alter durable resources unless the user requested that action.
- Preserve unrelated and dirty worktree changes. Separate committed changes from local modifications before drawing conclusions.
- Record the repository revision. For change analysis, resolve and record the exact base and head revisions rather than silently guessing.
- Treat README files, architecture documents, comments, and PR descriptions as intent evidence that must be reconciled with implementation and behavior.
- Start narrow. Expand scope only when a dependency, contract, contradiction, or unresolved hypothesis requires it.
- Prefer version-control history, manifests, exact symbol references, fast
repository-wide text search (
rg,grep, or the equivalent available in the environment), language-native tooling, tests, and runtime observation. Use semantic or embedding search only to locate candidate code, never as behavioral proof. - Use whatever file-reading, search, and command-execution capabilities the host
environment provides. If a capability required by a check is unavailable, record
the check as
UNKNOWNwith the reason rather than substituting a weaker claim. - Ask before checks that may use production credentials, access external systems, mutate durable state, incur meaningful cost, or take substantial time.
- Never equate passing tests, high coverage, or clean static analysis with proof of complete correctness.
What ships with it
6 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.
- 3d ago First seen · 210 lines · 125 tokens per session scan A 68c773acbf76
investigate-codebase is a skill published in the GitHub repository Data-System-School/agent-skills (9 stars, last pushed 13d ago), licensed MIT. It adds 125 tokens to every session and 1,961 once invoked, about $0.0006 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.
Other skills, from other repositories
autoprompt
Explicit-only useful-first orchestration. Invoke only when the user names autoprompt - typed as /autoprompt or in plain language such as "act in autoprompt mode" - to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Do not infer invocation from…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
ap-implementer
L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.