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/bostonaholic/team/researching-codebasesnpx skills add bostonaholic/team --skill researching-codebasesgit clone --depth 1 https://github.com/bostonaholic/teamWrote 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/bostonaholic/team/researching-codebases)<a href="https://agentmods.dev/skills/bostonaholic/team/researching-codebases"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/researching-codebases.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 | $0.00040 | $0.00761 |
| Opus 5 | $0.00020 | $0.00380 |
| Sonnet 5 | $0.00008 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
researching-codebases 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 today.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researching Codebases
The researcher's procedure: answer a list of neutral research questions with compressed, objective, file-referenced findings.
Investigation contract
Answer every question in questions.md, scoped by its "Codebase context"
section — and by repos.md when present (each repo's slug and absolute
path; which repo each question targets). How you investigate is yours to
choose. The output format below defines what complete findings look like;
two constraints hold on the way there:
- Evidence over recall. Every claim traces to code you read in this
run — cite file:line. When a question concerns behavior, follow the
execution path far enough to see the code that runs, not just a name
that suggests it.
A claim earns its place only with cited evidence (
skills/principle-evidence-over-assertion/SKILL.md). - Cross-repo contracts are findings. In multi-repo mode, contracts
that cross repo boundaries (shared types, API schemas) go in
## Constraints, and conventions that differ between repos go in## Patterns Observed.
Output format
Report findings in this structure. Keep the entire report under 100
lines (under 150 in multi-repo mode — extra budget for the per-repo
sections). The orchestrator writes the findings to
docs/plans/<id>/research.md.
In multi-repo mode, prefix every file reference with the repo slug,
e.g. frontend:src/App.tsx:42. The slug is the name field from the
matching entry in repos.md.
## Tech Stack
- Language, framework, key libraries with versions if visible
(multi-repo: list per repo, e.g. "frontend: React 18; api: Go 1.22")
## Directory Conventions
- How the codebase is organized, where things go
(multi-repo: one bullet per repo)
## Answers to Questions
### Q1: <restate question>
<answer with file:line references>
### Q2: <restate question>
<answer with file:line references>
...
## Patterns Observed
- How the codebase implements similar concerns
- Error handling conventions
- Naming conventions
## Test Patterns
- Test framework and assertion style
- Test file location convention
- Fixture/helper patterns
## Reusable Components
- Existing utilities, helpers, or abstractions
- Shared types or interfaces
## Constraints
- Hard constraints (type contracts, schema requirements, API compatibility)
- Soft constraints (conventions worth following for consistency)
## Open Questions
- Anything ambiguous that the design-author should resolve with the user
What ships with it
1 file 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.
- today Changed · +3 lines 19bd92c3ed44
- 4d ago First seen · 89 lines · 40 tokens per session scan A 5527dd7832a1
researching-codebases is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 761 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
analyze-performance-traces
Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and…
tutti-test-audit
Audit, design, write, materially revise, or remove Tutti tests. Use whenever Codex changes or reviews unit, component, conformance, integration, regression, platform, or repository tests; enforce a protected product contract, credible failure, correct owning boundary, negative-control evidence, overlap review…
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
assimilate-popular-workflows
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
babysit-babysitter-issues
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.
babysit
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.).