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 Siddhant-K-code/agent-trace --skill agent-stracegit clone --depth 1 https://github.com/Siddhant-K-code/agent-traceWrote 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/siddhant-k-code/agent-trace/agent-strace)<a href="https://agentmods.dev/skills/siddhant-k-code/agent-trace/agent-strace"><img src="https://agentmods.dev/badge/skills/siddhant-k-code/agent-trace/agent-strace/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/siddhant-k-code/agent-trace/agent-strace"><img src="https://agentmods.dev/badge/skills/siddhant-k-code/agent-trace/agent-strace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.00402 |
| Opus 5.5 | $0.00022 | $0.00161 |
| Sonnet 5.5 | $0.00011 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
agent-strace 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 1mo 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.
What it actually says
agent-strace
Use the local agent-strace executable. The plugin contributes lifecycle hooks,
but the Python package must also be installed and available on PATH.
Prerequisite check
Run agent-strace --version. If it is unavailable, stop and provide one of:
uv tool install agent-strace
pip install agent-strace
Do not silently substitute another tracing tool.
Capture
Installed plugin hooks automatically record new Copilot CLI sessions to
.agent-traces/. Do not also run agent-strace setup --cli copilot; that would
register duplicate hooks.
Investigate
Choose the smallest command set that answers the request:
agent-strace list
agent-strace inspect <session-id>
agent-strace replay <session-id>
agent-strace explain <session-id>
agent-strace timeline <session-id>
agent-strace why <session-id> <event-number>
agent-strace lint <session-id>
agent-strace audit <session-id>
agent-strace cost <session-id>
agent-strace diff <session-a> <session-b>
agent-strace compare <session-a> <session-b>
Resolve an omitted session ID with agent-strace list. Prefer text output for
interactive analysis and JSON only when structured processing is necessary.
Report exact session IDs and event numbers for material findings.
Safety
- Treat trace storage as read-only unless the user requests retention, import, anonymization, or another mutating operation.
- Preserve secret redaction.
- Do not claim causal intent from proximity alone; use
whyor clearly label the conclusion as an inference.
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.
- 1mo ago First seen · 57 lines · 54 tokens per session scan A 2fb5b3651d9d
agent-strace is a skill published in the GitHub repository Siddhant-K-code/agent-trace (96 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 402 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
adk-debug
Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the adk run CLI and the adk web dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the wrong answer, ignores a tool or swallows a tool error, hangs…
resolve-handoff
Emit the complete Resolve handoff with exact modes, outcomes, test evidence, and publication state.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests against…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, resolve/search/record, graph workbench reads/writes, resource (document payload) commands, and pot scope behavior.