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 Kastalien-Research/thoughtbox --skill researching-codebasesgit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/kastalien-research/thoughtbox/researching-codebases)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/researching-codebases"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/researching-codebases/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/kastalien-research/thoughtbox/researching-codebases"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/researching-codebases.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 | $0.00039 | $0.00630 |
| Opus 5.5 | $0.00016 | $0.00252 |
| Sonnet 5.5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- researching-codebases — 100% identical, 0 lines differ
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
Coordinate parallel sub-agents to answer complex codebase questions.
When to Use
- Questions spanning multiple files or components
- "How does X work?" requiring tracing through code
- Finding patterns or examples across the codebase
- Understanding architectural decisions or data flow
When NOT to Use
- Simple "where is X?" - use
code-locatordirectly - Single file questions - just read the file
- External/web research only - use
web-searcherdirectly
Workflow
0. Check past research (optional)
Before decomposing a new research question, consider checking for related past research:
- Run
list-research.pyscript to see recent research docs - Run
search-research.pyscript with relevant keywords - If related research exists, run
read-research.pyscript to load it - Build on previous findings instead of starting fresh
See research-tools.md for script usage.
1. Read mentioned files first
If the user references specific files, read them FULLY before spawning agents. This gives you context for decomposition.
2. Decompose the question
Break the query into parallel research tasks. Consider:
- Which areas of the codebase are relevant?
- Do I need locations, analysis, or examples?
- See
agent-selection.mdfor agent capabilities
3. Spawn parallel agents
Launch multiple agents concurrently for independent tasks. Use the task tool with appropriate subagent_type.
Wait for ALL agents to complete before synthesizing.
4. Synthesize and respond
Combine findings into a coherent answer:
- Direct answer to the question
- Key
file:linereferences - Connections between components
- Open questions if any areas need more investigation
5. Offer to save (optional)
For substantial research, ask:
Want me to save this to a research doc? (project:
.research/or global:~/.research/)
Skip this for quick answers.
When saving:
- Run
gather-metadata.pyscript to get date, repo, branch, commit, cwd. - Add query (from user's question) and tags (from content)
- Format YAML frontmatter per
output-format.md - Create directory if it doesn't exist
- Use filename:
{filename_date}_topic-slug.md
What ships with it
13 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.
- agent-selection.md 1.5 KB
- agents/code-analyzer.md 4.3 KB
- agents/code-locator.md 3.7 KB
- agents/code-pattern-finder.md 5.6 KB
- agents/README.md 1.0 KB
- agents/web-searcher.md 5.0 KB
- output-format.md 2.5 KB
- research-tools.md 2.1 KB
- scripts/gather-metadata.py 1.5 KB runs code
- scripts/list-research.py 4.6 KB runs code
- scripts/promote-research.py 1.2 KB runs code
- scripts/read-research.py 1.4 KB runs code
- scripts/search-research.py 5.5 KB runs code
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.
- 1mo ago First seen · 92 lines · 39 tokens per session scan A cf8ca2b6e039
researching-codebases is a skill published in the GitHub repository Kastalien-Research/thoughtbox (65 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 630 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
unity-yaml-editing
Last-resort guidance for safely hand-editing Unity YAML.
ad-policy-check
Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the copy, on-image or on-screen text, pictures and people. Rewrites what can be fixed honestly, adds the disclosures that are needed, and flags anything that needs a human or legal review, with…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…