A code-investigation guide for understanding unfamiliar code, tracing how data and calls move through a program, and finding the supported cause of a failure or regression. It can also use project history to explain when and why behavior changed.

Use it to follow callers and symbols, investigate reproducible failures or data and timing problems, compare old and new behavior, or choose a suitable code-navigation tool.

It keeps investigation evidence-based and read-only, so you can distinguish a confirmed cause from an assumption before changing code.

code-trace — Skill for Claude Code and Codex by hmj1026/dhpk

Install

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.

Any agent

npx skills add hmj1026/dhpk --skill code-trace

Clone the repo

git clone --depth 1 https://github.com/hmj1026/dhpk

Made for: Claude Code, Codex.

Or install dhpk, the plugin that ships this one along with the rest of its 39 skills, 1 command, 1 agent, 3 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hmj1026/dhpk/code-trace/github.svg)](https://agentmods.dev/skills/hmj1026/dhpk/code-trace)

Your own site

<a href="https://agentmods.dev/skills/hmj1026/dhpk/code-trace"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/code-trace/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hmj1026/dhpk/code-trace"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/code-trace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,713 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00081	$0.01713
Opus 5.5	$0.00032	$0.00685
Sonnet 5.5	$0.00016	$0.00343
Haiku 4.5	$0.00008	$0.00171

Measured yesterday against content hash 4b9194d968e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-trace 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.

The scan reads SKILL.md. This mod also ships 11 executable files (references/dhpk-repo-intake/scripts/intake_cached.js, references/dhpk-repo-intake/scripts/lib/runner-utils.js, references/dhpk-repo-intake/scripts/scan_delta.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

generated/claude-marketplace/package/skills/code-trace/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Trace

Use the smallest mode that answers the question. The default stance is evidence-first and read-only: inspect the repository, trace the relevant boundary, and report what remains unknown. A diagnosis may recommend a repair or a regression test, but it does not implement the repair.

Modes

Mode	Use when	Completion criterion
`explore`	You need to understand an unfamiliar symbol, file, module, or flow.	Entry point, caller/callee path, evidence, assumptions, and gaps are recorded.
`diagnose`	A failure, regression, performance problem, data inconsistency, or timing issue needs a confirmed cause.	One falsifiable root cause is supported by evidence, or the current blocker and next check are explicit.
`history`	You need to know when, why, or by whom behavior changed.	Blame, timeline, original/problematic comparison, and actionable conclusion are reported.
`select-tool`	You need one code-navigation tool and a fallback chosen.	One intent row, executable primary call, and concrete fallback or `none` are returned.

If --mode is omitted, infer one mode only when intent is unambiguous. A request to edit a symbol first requires the repository's impact-analysis rule before any implementation lane touches it; this skill only reports the impact.

When NOT to Use

Implement a confirmed change → use flow-drive.
Review a proposed change → use change-verdict.
Review an existing skill document or change → use change-verdict in its docs or risk mode. Specialized skill governance scoring and stocktake are retired.

`explore`

Identify the repository root, question, entry point, and target symbol.
Follow the repository's CX priority: use cx overview, then cx definition, then cx references for symbol-level questions. Use the selected semantic fallback only when CX cannot answer.
Trace callers, callees, data/control transitions, and observable output until the relevant boundary is accounted for.
For --dual, dispatch an isolated read-only perspective with only the original question, repository path, and depth. Reconcile evidence after the primary trace; never seed the second perspective with a conclusion.
For --explain --depth brief|normal|deep, keep the response within the requested depth. Load references/explore/ only for the selected branch.

Read the full file on GitHub · 157 lines

Files

What ships with it

35 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.

Changes

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 Changed · +8 lines 4b9194d968e7
10d ago Changed · +13 lines fed1685690b0
1mo ago First seen · 136 lines · 81 tokens per session scan A 109309d5a6f2

Subscribe to this mod's changes

code-trace is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,713 once invoked, about $0.0003 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 2026-09-05.

Claude Code Debugging OpenSpec ai-tooling claude-code-plugin harness

generator-apply-fixes

Internal Auto-Harness generator skill for QA fix cycles. Use only inside the Generator subagent when it is addressing named defects from QA or retest.

redker56/auto-harness · 36 tokens

anti-patterns

Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).

avelikiy/great_cto · 59 tokens

windows-compat

Audit and harden this Rust repo (code-graph-mcp) for Windows correctness: path-spelling drift between producers, the 32,767-char command-line cap, index-key mismatches, and path predicates that assume one ecosystem's layout. Use whenever touching code that builds, compares, prints, or stores a filesystem path; that…

sdsrss/code-graph-mcp · 165 tokens

chaos

Design, run, and debug Chaos Engineering experiments on Kubernetes using Litmus Chaos v3 and Chaos Mesh v2. Covers fault injection (pod-delete, network-loss, CPU stress, node-drain), steady-state hypothesis probes, GameDay runbooks, scheduled experiments, DORA feedback loop, and RBAC setup. Use when asked to "inject a…

nitinjain999/platform-skills · 97 tokens

incremental-analysis

Detect existing workspace, diff current sources against high water mark metadata, classify specs as unchanged/stale/orphaned/new, re-analyze only what changed. Activates automatically when /analyze finds an existing workspace.

prime-radiant-inc/greenfield · 47 tokens

Hallucinated Reference 幻覚的参照の実在確認

A code review check that verifies newly added imports, function calls, methods, and library APIs actually exist. An API is a defined way for code to use another module or service.

s977043/river-review · 93 tokens