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/fikrilal/engineering-agent-skills/orient-codebasenpx skills add fikrilal/engineering-agent-skills --skill orient-codebasegit clone --depth 1 https://github.com/fikrilal/engineering-agent-skillsWhat 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 | $0.00059 | $0.00538 |
| Opus 5 | $0.00030 | $0.00269 |
| Sonnet 5 | $0.00012 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
orient-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 2d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orient Codebase
Build an evidence-grounded map that helps the learner reason about the system. Do not produce an exhaustive file inventory.
Workflow
- Establish the learner context from the conversation. Identify known languages, frameworks, and architectural patterns. Ask only when missing context would materially change the explanation.
- Read repository instructions and source-of-truth documents first. Then inspect manifests, build scripts, CI, entry points, and the top-level tree.
- Identify the product shape, deployed processes, runtime boundaries, persistence, external systems, and primary user workflows.
- Trace at least one representative vertical path from entry point to observable result. Use this path to make abstract boundaries concrete.
- Distinguish architectural intent documented by the repository from structure inferred from code.
- Identify only the highest-leverage reading targets and material uncertainties.
- Stop once the learner has a useful map. Offer deeper exploration by workflow or module instead of front-loading every detail.
Output
Default to this compact shape:
- System in one paragraph: what it does and how it runs.
- System map: major boundaries and where state lives, using a short list or text diagram.
- Start here: three to five files or workflows that build the mental model fastest.
Include a representative workflow when it makes the map easier to understand. Leave build commands, exhaustive module lists, documentation drift, and deeper risks for follow-up unless they are essential.
Explanation Rules
- Ground important claims in source files, configuration, tests, or recorded command output.
- Use file and line references when the client supports them.
- Start with purpose and observable behavior, then reveal implementation detail.
- Adapt explanations to knowledge already stated by the learner.
- Use plain words and short sentences. Give the answer before supporting detail.
- State uncertainty only when it changes the mental model.
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.
- 2d ago First seen · 48 lines · 59 tokens per session scan A bc3e542b43c1
orient-codebase is a skill published in the GitHub repository fikrilal/engineering-agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 538 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…