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 skills add fikrilal/engineering-agent-skills --skill trace-behaviorgit clone --depth 1 https://github.com/fikrilal/engineering-agent-skillsWrote 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.
[](https://agentmods.dev/skills/fikrilal/engineering-agent-skills/trace-behavior)<a href="https://agentmods.dev/skills/fikrilal/engineering-agent-skills/trace-behavior"><img src="https://agentmods.dev/badge/skills/fikrilal/engineering-agent-skills/trace-behavior/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.
<a href="https://agentmods.dev/skills/fikrilal/engineering-agent-skills/trace-behavior"><img src="https://agentmods.dev/badge/skills/fikrilal/engineering-agent-skills/trace-behavior.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00072 | $0.00467 |
| Opus 5.5 | $0.00029 | $0.00187 |
| Sonnet 5.5 | $0.00014 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
trace-behavior 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 2mo 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trace Behavior
Follow real control flow and data flow across boundaries until the observable outcome is explained.
Workflow
- Restate the behavior as a concrete trigger and expected observable result.
- Read repository instructions, then locate the true entry point using search and call sites. Do not begin from a similarly named helper without confirming reachability.
- Follow control flow across UI, transport, application, domain, infrastructure, persistence, and external-process boundaries as applicable.
- Track important data alongside control flow: creation, validation, transformation, ownership, persistence, and presentation.
- Record branching, async handoffs, retries, cancellation, timeouts, caching, deduplication, and transaction boundaries when present.
- Trace failure or recovery only when it affects the requested behavior or explains an observed problem.
- Mark runtime behavior that static inspection cannot resolve.
Output
Default to this compact shape:
- In short: two or three sentences describing the trigger and result.
- Flow: a numbered runtime sequence with inline file references.
- Important detail: state ownership, persistence, async behavior, or failure handling only when needed.
For complex flows, include a compact text sequence diagram. Do not use a diagram when a short numbered sequence is clearer.
Explanation Rules
- Ground each important step in reachable code, runtime composition, or configuration.
- Explain ownership: which component decides, stores, transforms, or transports.
- Use the learner's known concepts only when the analogy is structurally accurate.
- Give the shortest complete trace first and expand on request.
- State uncertainty only where static inspection cannot establish runtime behavior.
Guardrails
- Do not modify files or runtime state.
- Do not stop at interface declarations; find concrete composition and implementations.
- Do not present inferred runtime behavior as confirmed.
- Avoid unrelated architecture commentary; stay centered on the requested behavior.
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.
- 2mo ago First seen · 45 lines · 72 tokens per session scan A 1edea4482359
trace-behavior is a skill published in the GitHub repository fikrilal/engineering-agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 467 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
ci-fixer
CI failures - read error, minimal fix, verify.
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…