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/ezraapple/skills-init/trace-codebasenpx skills add EzraApple/skills-init --skill trace-codebasegit clone --depth 1 https://github.com/EzraApple/skills-initWhat 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 | $0.00051 | $0.00790 |
| Opus 5 | $0.00026 | $0.00395 |
| Sonnet 5 | $0.00010 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
trace-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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trace Codebase
Produce an evidence-backed map of a subsystem that is smaller than the code explored. Explain the representative flow, ownership boundaries, and change seams without turning the result into an encyclopedia.
Route Nearby Work
- Use
systematic-debuggingfor an active failure needing a causal diagnosis. - Use
plan-changesonce the task is to choose and sequence modifications. - Use review skills for evaluating an existing diff.
- Answer small factual lookups directly.
Resolve the Scope
Translate the requested area into concrete paths, symbols, routes, commands, or runtime entrypoints.
Start with cheap discovery:
- repository guidance and package manifests;
- directory and export structure;
- named routes, commands, events, schemas, or UI entrypoints;
- tests and examples that exercise the behavior;
- direct callers and consumers.
If the area is large, select one representative flow and state what is excluded. Ask for clarification only when different interpretations would produce materially different maps.
Trace a Representative Flow
Follow real code through the relevant stages:
external entry -> validation/auth -> orchestration/domain logic
-> persistence or external side effect -> returned or visible result
Adapt the stages to the system. Capture:
- where execution starts;
- the important data shapes and contracts;
- where decisions and invariants live;
- state ownership and lifecycle;
- error and cancellation behavior;
- persistence, network, queue, filesystem, or process boundaries;
- configuration, generated code, and feature gates that change behavior;
- the consumers that constrain safe changes.
Read enough surrounding code to distinguish a real boundary from a helper that only forwards data.
Use History Selectively
Read git history, issue context, or design docs when they can explain:
- why a surprising boundary exists;
- whether behavior is a compatibility constraint;
- where a regression or migration began;
- which prior approach should be reused or avoided.
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 · 125 lines · 51 tokens per session scan A 75b33dd786bf
trace-codebase is a skill published in the GitHub repository EzraApple/skills-init (2 stars, last pushed 29d ago), licensed MIT. It adds 51 tokens to every session and 790 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
etsy-category-listing
Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…
human-approval
Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…
firebase-analytics
Use when logging analytics events, setting user properties, configuring default event parameters, building funnels, or adding screen-view tracking.
firebase-remote-config
Use when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config, or enabling real-time config updates.
git-master
MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git…
prismer-evolve-record
Record the outcome of applying an evolution strategy. Use after resolving an error where prismer-evolve-analyze provided a recommendation, to feed back success or failure to the network.