codebase-search
Skill230 starsChanged 5 months agoMITView on GitHub
Task-specific local codebase-understanding workflow for OpenCode, MCP, Pi, omp, and Codex. Use compact context for unfamiliar repository orientation, direct definition and graph tools for known targets.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- tmcfarlane/team-avatartheir own version, first seen Oct 20, 2026
- FilenCloudDienste/filen-rstheir own version, first seen Oct 9, 2026
- derheissenberg/applicaitontheir own version, first seen May 20, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- tmcfarlane/team-avatar★ 112same name
- FilenCloudDienste/filen-rs★ 104same name
- derheissenberg/applicaiton★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- AGENTS.mdAGENTS.md
- codebase-searchSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 1 is distinctive, and 7 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when you need local repository knowledge before web lookup.
- Very specific: line 12
Run index_status when index readiness or freshness is unknown.
- Very specific: line 13
When repository orientation is needed (layout, relevant symbols, or cross-file intent), use one compact codebase_context(query, …
- Very specific: line 16
Use codebase_peek(query, ...) when only semantic locations are needed, and codebase_search(query, ...) when matching source content is …
- Very specific: line 17
Read known paths directly and use grep for exact identifiers or exhaustive literal matches.
- Very specific: line 19
Avoid repeating broad reads or retrieval when existing evidence already answers the question.
- Very specific: line 45
Use grep for exact identifiers and tiny, deterministic lookups.
- Very specific: line 46
Use websearch only when local tools return no results and docs are likely missing.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Codebase Search Skill
Use this skill when you need local repository knowledge before web lookup.
Core workflow
- Run
index_statuswhen index readiness or freshness is unknown. - When repository orientation is needed (layout, relevant symbols, or cross-file intent), use one compact
codebase_context(query, tokenBudget: 600, limit: 5)first pass and inspect returned evidence before broad reads or searches. Do not call it mechanically before every task or tool. - For a known definition, use
implementation_lookup(query)directly. For callers or callees, usecall_graph(name, direction)directly; for relationships between identified endpoints, usecall_graph_path(from, to)directly. - For a change with a known or suspected target symbol, optionally use
codebase_edit_contextfor bounded target source plus direct callers and callees. - Use
codebase_peek(query, ...)when only semantic locations are needed, andcodebase_search(query, ...)when matching source content is needed. Neither requires another context call when the task is already scoped. - Read known paths directly and use
grepfor exact identifiers or exhaustive literal matches. Usefind_similar(code)for analogous implementations and duplicates.
Avoid repeating broad reads or retrieval when existing evidence already answers the question. If results are weak, check readiness, compatibility, and scope with index_status; run index_codebase only when the index is missing, stale, or incompatible.
Tool Priority
codebase_contextfor compact, unfamiliar-repository orientation; explicitsymbolandfrom+torouting remains supported.implementation_lookupfor known definitions.call_graphandcall_graph_pathfor relationships once symbols or endpoints are identified.codebase_edit_contextas an optional bounded pre-edit step.codebase_peekfor metadata-only semantic locations.codebase_searchfor matching implementation content.find_similarfor pattern matching and duplication.index_codebase(force/estimate/dryRun/verbose) for first-time or stale indexes.index_status,index_health_check,index_metrics,index_logsfor operational checks.
Suggested Commands
- Unfamiliar subsystem:
codebase_context("payment processing flow", tokenBudget: 600, limit: 5). - Known definition:
implementation_lookup("validate"). - Callers or callees:
call_graph("chargeCard", "callees"). - Known endpoints:
call_graph_path("submitPayment", "chargeCard"). - Change target:
codebase_edit_context(query: "reject expired tokens", symbol: "validateToken"). - Matching source after scope is known:
codebase_search("payment retry guards"). - Analogous code:
find_similar("function validate(data)").
Additional Notes
- Use
grepfor exact identifiers and tiny, deterministic lookups. - Use
websearchonly when local tools return no results and docs are likely missing. - Choose the next tool from the evidence needed, not a mandatory context → peek → search chain.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

