Production Audit
affaan-m/ECC
Local-evidence production readiness audit for shipped apps, pre-launch reviews, post-merge checks, and "what breaks in prod?" questions without sending repo data to an external audit service.
A skill your agent uses when tracing or auditing Tau agent execution, including provider and cache cost, tool/background/wait latency, outer turns, compaction, delegated workflows, or performance…
MPL-2.0Auto-check passed
Install Tau Agent Tracing
$ npx skills add dpc/tau --skill tau-agent-tracing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dpc/tau tau-agent-tracing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/dpc/tau.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/tau-agent-tracing .claude/skills/tau-agent-tracing && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "tau-agent-tracing" agent skill from https://github.com/dpc/tau/tree/master/.agents/skills/tau-agent-tracing into .claude/skills/tau-agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tau-agent-tracing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/dpc/tau/tree/master/.agents/skills/tau-agent-tracingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add dpc/tau --skill tau-agent-tracing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dpc/tau tau-agent-tracing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dpc/tau.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/tau-agent-tracing .agents/skills/tau-agent-tracing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tau-agent-tracing" agent skill from https://github.com/dpc/tau/tree/master/.agents/skills/tau-agent-tracing into .agents/skills/tau-agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tau-agent-tracing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dpc/tau --skill tau-agent-tracing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dpc/tau tau-agent-tracing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dpc/tau.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/tau-agent-tracing .cursor/skills/tau-agent-tracing && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "tau-agent-tracing" agent skill from https://github.com/dpc/tau/tree/master/.agents/skills/tau-agent-tracing into .cursor/skills/tau-agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tau-agent-tracing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/dpc/tau.git --path .agents/skills/tau-agent-tracing--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add dpc/tau --skill tau-agent-tracing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dpc/tau tau-agent-tracing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dpc/tau.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/tau-agent-tracing .gemini/skills/tau-agent-tracing && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "tau-agent-tracing" agent skill from https://github.com/dpc/tau/tree/master/.agents/skills/tau-agent-tracing into .gemini/skills/tau-agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tau-agent-tracing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install dpc/tau tau-agent-tracingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add dpc/tau --skill tau-agent-tracing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dpc/tau.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/tau-agent-tracing .github/skills/tau-agent-tracing && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "tau-agent-tracing" agent skill from https://github.com/dpc/tau/tree/master/.agents/skills/tau-agent-tracing into .github/skills/tau-agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tau-agent-tracing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dpc/tau --skill tau-agent-tracing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dpc/tau tau-agent-tracing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dpc/tau.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/tau-agent-tracing .opencode/skills/tau-agent-tracing && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "tau-agent-tracing" agent skill from https://github.com/dpc/tau/tree/master/.agents/skills/tau-agent-tracing into .opencode/skills/tau-agent-tracing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tau-agent-tracing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
tau-agent-tracing- GitHub stars
- 104
- Token cost
- ~658 tokens
- SKILL.md length
- 240 words
- Files
- 1
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- MPL-2.0
At a glance
A skill your agent uses when tracing or auditing Tau agent execution, including provider and cache cost, tool/background/wait latency, outer turns, compaction, delegated workflows, or performance…
- Auditing Tau agent execution
- Calls jq
- Including provider and cache cost
- Tool/background/wait latency
What it does
Tau Agent Tracing is an agent skill from dpc/tau. Use this skill when tracing or auditing Tau agent execution, including provider and cache cost, tool/background/wait latency, outer turns, compaction, delegated workflows, or performance regressions from durable agent journals.
Its SKILL.md is about 660 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Tau Coding Agent - like Pi, but twice as much. The licence is MPL-2.0.
When your agent uses it
- Auditing Tau agent execution
- Including provider and cache cost
- Tool/background/wait latency
- Delegated workflows
Example prompts
- “/tau-agent-tracing”
What it can do on your machine
Read from SKILL.md and the folder at commit d2e1955. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
jq
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Tau Agent Tracing loads about 658 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 240 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from dpc/tau at commit d2e1955, republished under its MPL-2.0 licence (© dpc). 240 words, ~658 tokens.
Download SKILL.mdSave it as
.claude/skills/tau-agent-tracing/SKILL.md (or your agent's skills folder).- name
- tau-agent-tracing
- description
- Use this skill when tracing or auditing Tau agent execution, including provider and cache cost, tool/background/wait latency, outer turns, compaction, delegated workflows, or performance regressions from durable agent journals.
- user-invocable
- true
- advertise
- true
Trace Tau agent execution
Start content-free and include the workflow when relevant:
trace=$(mktemp)
chmod 600 "$trace"
tau agent trace <agent-id> --include-descendants \
--format agent-performance-jsonl >"$trace"
jq -c 'select(.record_type != "header")' "$trace"This view covers ordinary provider accounting, tool/background lifecycle, typed waits, outer turns, and standalone compaction without prompt, tool, or response bodies. Useful filters include:
jq -c 'select(.record_type=="wait" and .outcome=="interrupted_by_activation")' "$trace"
jq -s 'map(select(.record_type=="provider_prompt")) | sort_by(.recorded_at_wall_elapsed_us // 0) | reverse | .[:10]' "$trace"Use agent-tools-toon or agent-tools-jsonl only to explain an identified
interval. Prefer the default lite/bounded output; use --mode full only when the
bounded payload cannot answer the question. Use tau-jsonl only for
journal-integrity or replay questions: it is the complete canonical artifact,
not the default performance view.
Escalate outside trace only for facts trace intentionally does not own: session
events.jsonl for transient runtime observations, private provider captures for
exact wire/request shape, and component logs for operational failures. Load
tau-self-knowledge-debugging for that workflow.
Interpret intervals narrowly. Journal sequence is authoritative only within one
agent. Cross-agent timestamp order is presentation, not causality; only explicit
references justify relationships. *_us measures append-invocation wall time,
not CPU, wire, model, or commit time, and totals can overlap. A running-agent
trace uses a validated checkpoint prefix and may omit the newest writes.
Performance JSONL contains no prompt/tool body, but it still exposes IDs, model,
activity timing, token/cache/cost, membership, and work patterns. Compact and
tau-jsonl outputs additionally expose unredacted reasoning, messages,
arguments, output, and possibly secrets. Keep traces private, use owner-only
files, do not put them in /tmp/public, reports, tickets, or commits, and delete
temporary artifacts.
docs/agent-trace.md owns exact schemas. Built-in
tau-self-knowledge-tracing covers installed Tau usage, and
tau-self-knowledge-debugging owns lower-level logs and captures.
© dpc, MPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/tau-agent-tracing of dpc/tau.
Open the folder on GitHubat commit d2e1955
Compare with similar skills
Tau Agent Tracing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Tau Agent Tracing this skilldpc/tau | 104 | — | ~658 | Automated safety check: Pass | MPL-2.0 | |
| Production Auditaffaan-m/ECC | 275k | 1 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Aims Auditalirezarezvani/claude-skills | 28k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Geo Auditsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.4k | Automated safety check: Notes | MIT | |
| Audit Preparationsickn33/agentic-awesome-skills | 47k | 1 repos | ~5.3k | Automated safety check: Pass | MIT | |
| OmniRoute Audit and Policy CLIdiegosouzapw/OmniRoute | 74k | 1 repos | ~733 | Automated safety check: Pass | MIT |
Similar skills
Aims Audit
alirezarezvani/claude-skills
/cs:aims-audit <scope — ISO/IEC 42001 AIMS internal-audit 6-question forcing interrogation.
Geo Audit
sickn33/agentic-awesome-skills
Full website GEO+SEO audit with parallel subagent delegation.
Audit Preparation
sickn33/agentic-awesome-skills
Audit preparation register: required document, period covered, request and receipt dates, preparer and reviewer, auditor queries and adjustments.
OmniRoute Audit and Policy CLI
diegosouzapw/OmniRoute
Command reference for omniroute's audit, logs, policy and telemetry commands: search and export audit trails, manage access policies and review request history for compliance work.
Qms Audit Expert
davila7/claude-code-templates
Senior QMS Audit Expert for internal and external quality management system auditing.
More from dpc/tau
All 15 skills in this repoTau Cargo Crap
dpc/tau
A skill your agent uses when selfci, Nix CI, coverage, cargo-crap, CRAP-score, crapAbsolute, or crapReport checks fail in Tau, or before changing the cargo-crap gates, thresholds, or flagged complex…
Tau Papercut Triage
dpc/tau
A skill your agent uses when asked to "triage papercuts", review clanker-reported problems, or analyze and clear tau dev papercut reports.
Tau Tool Verification
dpc/tau
A skill your agent uses when asked to verify Tau harness tools or tool output behavior, especially read, edit, shell/shellcommand, line-oriented output, truncation, metadata headers, UTF-8 handling…
A skill your agent uses when verifying Tau file and command tools: read, edit, replace, applypatch, shell, or shellcommand, including ranges, UTF-8, truncation, diffs, timeouts, mutation safety, and…
Preview Site
dpc/tau
A skill your agent uses when changing or reviewing Tau's static site under site/ and needing visual verification of layout, spacing, colors, alignment, desktop rendering, mobile rendering, or…
A skill your agent uses when verifying Tau agentstart, message, or agentwatch coordination, including routing, validation, interruption, notification formatting, watch lifecycle, and deduplication.
Questions about Tau Agent Tracing
What does Tau Agent Tracing do?
A skill your agent uses when tracing or auditing Tau agent execution, including provider and cache cost, tool/background/wait latency, outer turns, compaction, delegated workflows, or performance…. Tau Agent Tracing is an agent skill from dpc/tau. Use this skill when tracing or auditing Tau agent execution, including provider and cache cost, tool/background/wait latency, outer turns, compaction, delegated workflows, or performance regressions from durable agent journals.
When should I use Tau Agent Tracing?
Tau Agent Tracing fits situations like: auditing Tau agent execution; including provider and cache cost; tool/background/wait latency; delegated workflows.
How do I install Tau Agent Tracing in Claude Code?
Run `npx skills add dpc/tau --skill tau-agent-tracing -a claude-code`. Or copy the skill folder (.agents/skills/tau-agent-tracing in dpc/tau) into .claude/skills/tau-agent-tracing in your project. Claude Code loads it when a task matches its description.
How do I install Tau Agent Tracing in Codex?
Run `npx skills add dpc/tau --skill tau-agent-tracing -a codex`. Or copy the skill folder (.agents/skills/tau-agent-tracing in dpc/tau) into .agents/skills/tau-agent-tracing in your project. Codex loads it when a task matches its description.
Can I use Tau Agent Tracing in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dpc/tau --skill tau-agent-tracing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tau-agent-tracing, .gemini/skills/tau-agent-tracing, .github/skills/tau-agent-tracing and .opencode/skills/tau-agent-tracing in your project.
What does Tau Agent Tracing need to run?
Going by SKILL.md and its folder, Tau Agent Tracing needs the command-line tools its instructions call (jq).
Does Tau Agent Tracing access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Tau Agent Tracing safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Tau Agent Tracing use?
Tau Agent Tracing is published under the MPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Tau Agent Tracing use?
About 658 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Tau Agent Tracing?
Skills that share tags, products or a category with Tau Agent Tracing: Production Audit (affaan-m/ECC, 275k stars), Aims Audit (alirezarezvani/claude-skills, 28k stars), Geo Audit (sickn33/agentic-awesome-skills, 47k stars) and Audit Preparation (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tau Agent Tracing?
dpc (a GitHub user) maintains it in dpc/tau, which has 104 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 5, 2026.
Source: dpc/tau on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.