audit-workstream-run

audit-workstream-run is a skill for Claude Code, Codex from ShivaeDev/pardes. It costs 56 tokens per session (437 once invoked), scanned A, original, MIT.

A review process for evaluating a completed or ongoing coding-agent session as a workflow, rather than judging only its code.

In plain words
What is it for?
It helps audit agent workflows and propose improvements to reusable orchestration instructions without changing them automatically.
Why use it?
It reveals where delegation, handoffs, worktrees, verification, pull-request monitoring, or recovery from lost context caused problems.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/shivaedev/pardes/audit-workstream-run
Any agent
npx skills add ShivaeDev/pardes --skill audit-workstream-run
Clone the repo
git clone --depth 1 https://github.com/ShivaeDev/pardes

Made for: Claude Code, Codex.

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.

agentmods badge for audit-workstream-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/shivaedev/pardes/audit-workstream-run.svg)](https://agentmods.dev/skills/shivaedev/pardes/audit-workstream-run)
Your own site
<a href="https://agentmods.dev/skills/shivaedev/pardes/audit-workstream-run"><img src="https://agentmods.dev/badge/skills/shivaedev/pardes/audit-workstream-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 437 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.00437
Opus 5 $0.00028 $0.00218
Sonnet 5 $0.00011 $0.00087
Haiku 4.5 $0.00006 $0.00044

Measured 3d ago against content hash 69832fd6c90a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-workstream-run 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 3d 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.

plugins/codex-workstreams/skills/audit-workstream-run/SKILL.md · 50 lines

What it actually says

Audit Workstream Run

Evaluate another Codex session without loading its full transcript into the manager context. Use the result to improve reusable workflow skills.

Workflow

  1. Read only lightweight metadata first:
    • ${CODEX_HOME:-$HOME/.codex}/session_index.jsonl
    • rollout filenames under ${CODEX_HOME:-$HOME/.codex}/sessions/
    • the first session_meta line when needed
  2. Identify the relevant user-started parent rollout and direct descendants by session ID and forked_from_id.
  3. Spawn a fresh read-only explorer to inspect the parent transcript and the minimum descendant transcript needed for a workflow audit.
  4. Ask the explorer to omit implementation detail unless it explains a process failure. Require verified evidence and a separate inference section.
  5. When the audit becomes the blocker, wait on the explorer with a 900000 ms timeout. Treat an ordinary timeout as still working and wait again without short polling.
  6. Present a compact audit and proposed skill improvements. Do not edit skills until the user approves the revision batch.

Explorer Brief

Request:

  • chronological workflow timeline
  • pipeline transitions and unnecessary branching
  • explorer, worker, and verifier delegation behavior
  • worker wait duration and repeated polling
  • worktree helper use and sandbox routing
  • PR-cycle publication, browser handoff, and monitor behavior
  • compaction or interrupted-wait recovery
  • actionable skill improvements ordered by impact
  • source pointers using session IDs and timestamps

Rules

  • Keep raw rollout JSONL out of the manager context.
  • Prefer one focused audit explorer over manager-side transcript reading.
  • Read descendant metadata and final reports first; expand only when needed.
  • Separate observed facts from hypotheses.
  • Evaluate the workflow, not the implementation.
Files

What ships with it

1 file 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.

  1. 3d ago First seen · 50 lines · 56 tokens per session scan A 69832fd6c90a

Subscribe to this mod's changes

audit-workstream-run is a skill published in the GitHub repository ShivaeDev/pardes (5 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 437 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens