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 agentmods add skills/shivaedev/pardes/configure-workstreamnpx skills add ShivaeDev/pardes --skill configure-workstreamgit clone --depth 1 https://github.com/ShivaeDev/pardesWhat 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 | $0.00040 | $0.00470 |
| Opus 5 | $0.00020 | $0.00235 |
| Sonnet 5 | $0.00008 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade B, and why
configure-workstream scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Explain the exact proposed filesystem and `~/.codex/config.toml` changes. What it actually says
Configure Workstream
Set up one visible artifact directory for manager-owned files. Keep the change narrow and explicit: inspect first, explain the proposed personal-config edit, and write only after the user approves it.
Diagnose
Run the read-only doctor:
uv run python -B "<configure-workstream-skill>/scripts/check_setup.py"
Read its JSON report. The recommended artifact directory is:
${CODEX_ARTIFACTS_DIR:-$HOME/codex-artifacts}
It contains workstreams/, pr-bodies/, and reports/.
Configure
- Explain the exact proposed filesystem and
~/.codex/config.tomlchanges. - Ask for explicit approval before editing personal config or creating directories.
- Preserve unrelated configuration and existing writable roots.
- If the user already uses permission profiles, add the artifact directory to
the selected profile's
workspace_roots. - Otherwise, add it to
sandbox_workspace_write.writable_roots. - Validate the resulting config with:
codex --strict-config --version
- Tell the user to start a new Codex session so the writable root takes effect.
For a stable legacy configuration, add the absolute artifact path:
[sandbox_workspace_write]
writable_roots = ["/absolute/path/to/codex-artifacts"]
For an existing permission profile, extend that profile:
[permissions.<profile>.workspace_roots]
"~/codex-artifacts" = true
Rules
- Never change personal config without explicit approval.
- Never migrate between legacy settings and permission profiles as part of onboarding.
- Never replace existing writable roots when adding the artifact directory.
- Never grant write access to the entire home directory.
- Keep source worktrees under
<primary-checkout>/.worktrees/. - Keep PR-monitor cursor state under
${CODEX_HOME:-$HOME/.codex}/state/pr-monitor/.
What ships with it
3 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.
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.
- 2d ago First seen · 70 lines · 40 tokens per session scan B c686df34a8cd
configure-workstream is a skill published in the GitHub repository ShivaeDev/pardes (5 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 470 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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 encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…