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 skills add akolotov/harness --skill research-codebasegit clone --depth 1 https://github.com/akolotov/harnessWrote 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/akolotov/harness/research-codebase)<a href="https://agentmods.dev/skills/akolotov/harness/research-codebase"><img src="https://agentmods.dev/badge/skills/akolotov/harness/research-codebase/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/skills/akolotov/harness/research-codebase"><img src="https://agentmods.dev/badge/skills/akolotov/harness/research-codebase.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 | $0.00135 | $0.02622 |
| Opus 5.5 | $0.00054 | $0.01049 |
| Sonnet 5.5 | $0.00027 | $0.00524 |
| Haiku 4.5 | $0.00014 | $0.00262 |
Grade A, and why
research-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 2mo 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Codebase
Investigate this project methodically, then leave behind a project-local research note that another engineer or AI agent can reuse.
This skill operates as a documentarian: it describes what exists, it does not recommend changes. The same constraint flows down to every sub-agent through the Sub-Agent Invocation Contract defined below.
Path Conventions
Paths in this document use <SKILL_DIR> to mean this skill's installation directory — for example .claude/skills/research-codebase in Claude Code, or .codex/skills/research-codebase in Codex CLI. Whenever you see <SKILL_DIR> in a Bash invocation or a Read directive (including directives this skill emits to sub-agents), substitute the actual installation path resolved from the harness. Markdown links to sibling files such as references/roles-overview.md are already relative to this file and need no substitution.
Initial Response
When invoked without a concrete research question, reply with:
I'm ready to research this codebase. Share the question or area you want investigated, and I'll trace the relevant code paths, summarize the findings, and capture the result in a project-local research note.
Then wait for the user's question.
Workflow
- Read any files the user names before decomposing the task. Read them fully (no
limit/offset). - Restate the question in precise technical terms and note the architectural implications likely to matter.
- Break the work into composable research areas. Decide which directories, files, interfaces, flows, or patterns must be investigated and which role (Locator / Analyzer / PatternFinder / WebResearcher) handles each one.
- Maintain a task list so every research area is tracked through synthesis.
- Delegate to sub-agents in parallel, one task per role pass. Construct each prompt by following the Sub-Agent Invocation Contract below.
- Start with Locator passes, follow with Analyzer passes on the most promising paths, add PatternFinder when comparable examples help, and use WebResearcher only when outside context is genuinely needed.
- Wait for all sub-agents to complete before synthesizing.
- Derive a short slug of 2–4 meaningful words for the research note.
- Run the metadata script (see "Metadata Script" below) to gather timestamps, target/workspace paths, git context, and the final note path.
- Write the research note to the path returned by the script.
- Present a concise answer with the most relevant file references, then ask whether the user wants follow-up research or clarification.
What ships with it
8 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.
- 2mo ago First seen · 209 lines · 135 tokens per session scan A 9c7ac9189219
research-codebase is a skill published in the GitHub repository akolotov/harness (2 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 2,622 once invoked, about $0.0005 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.
research-codebase compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| research-codebaseakolotov/harness | Skill | 2 | 1mo ago | MIT | A | 135 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |