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/kouroshez/coding-os/codebase-explorernpx skills add kouroshez/coding-os --skill codebase-explorergit clone --depth 1 https://github.com/kouroshez/coding-osWhat 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 | $0.00092 | $0.00887 |
| Opus 5 | $0.00046 | $0.00443 |
| Sonnet 5 | $0.00018 | $0.00177 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
codebase-explorer 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 yesterday.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore the specified conceptual area of the codebase and produce a structured map. Boundary with graph-explorer:
| Question shape | Use |
|---|---|
| "How does X work end-to-end?" | codebase-explorer |
| "What happens when a user does Y?" | codebase-explorer |
| "Where does this domain live?" | codebase-explorer |
"What calls function foo?" |
graph-explorer (cos_graph_references) |
"What breaks if I rename Bar?" |
graph-explorer (cos_graph_rename_plan) |
"Blast radius of changing baz?" |
graph-explorer (cos_graph_impact) |
codebase-explorer always consults graph-explorer for symbol-precise sub-questions during a conceptual walk — they compose, they don't compete.
Process
- Graph gate — If the query is an identifier-shaped symbol
(
camelCase,snake_case,Class.method,TASK-NNN, dotted path), trycos_graph_queryfirst. It is faster + more accurate than grep for named symbols AND returns confidence-scored edges. Fall back to grep only if the graph returns zero hits (fresh repo, unindexed file) or the query is conceptual ("auth flow", "money handling"). - Entry points — Use Grep to find the main files related to the topic.
- Trace the flow — Read key files, follow imports. When symbols
cross file boundaries, prefer
cos_graph_context(uid, depth=1)over chasing imports by hand — it returns the neighbourhood in a single MCP call. - Dependencies — Identify what this area depends on (models,
services, external APIs). For impact analysis, use
cos_graph_impact(uid, direction="downstream")— the plan's Formula-2 Step-10 tool. - Test coverage — Use Glob to find related test files. Graph edges
of type
tested_by(when present) point directly at them.
Output Format
Return a structured summary:
## [Area Name] — Codebase Map
### Entry Points
- file:line — description
### Data Flow
source → transform → destination
### Key Files
- path — responsibility
### Dependencies
- internal: models, services used
- external: APIs, packages
### Test Coverage
- test files found
- gaps identified
### Risks
- anything fragile, tightly coupled, or undocumented
What ships with it
3 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.
- yesterday First seen · 90 lines · 92 tokens per session scan A 7d8aa2428e24
codebase-explorer is a skill published in the GitHub repository kouroshez/coding-os (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 92 tokens to every session and 887 once invoked, about $0.0005 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
graph-mutation-plan
Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.
potpie-infra-architecture
Use for project infra and architecture context: environments, adapters, runtime configuration, deployments, service dependencies, datastores, API contracts, ownership, incidents, and dependency blast radius.
wiki-context-pack
Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task. Use for "/wiki-context-pack", "use my vault as context", "context slice for X", "pack the wiki for my agent", or "bounded context for Y".
alfworld-receptacle-finder
Searches for a suitable empty or appropriately occupied receptacle (like a shelf or table) to place an object. Use when you are holding an object that needs to be stored or placed and must find a receptacle that meets the placement criteria. Examines candidate receptacles by navigating to and inspecting each one until…
alfworld-search-pattern-executor
Systematically searches a sequence of likely locations for a target object based on common sense. Use when you need to find a specific object and know which receptacles to check but not which one contains it. Takes a list of candidate receptacles, orchestrates navigation and inspection, and outputs when the target is…
ux-ui-analyze-single-page
Analyze exactly one captured UI page (from uxuimap screenshots + request JSON) and immediately write/update uxuimap/pages/{page}.md in neutral descriptive language. Use when asked to analyze screenshots, rewrite corresponding analysis immediately, or avoid memory/context saturation.