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/drive-workstreamnpx skills add ShivaeDev/pardes --skill drive-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 | $0.00048 | $0.00709 |
| Opus 5 | $0.00024 | $0.00354 |
| Sonnet 5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
drive-workstream 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 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.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drive Workstream
Manage a substantial coding objective from initial understanding through a sequence of reviewed pull requests. Keep the main session focused on decisions, durable state, delegation, and user communication. The manager coordinates the work but does not implement or review code itself.
Pipeline
- Clarify the objective and constraints.
- Use
investigate-codebaseto gather evidence with read-only explorers. - Discuss the evidence, architecture, scope, and PR sequence with the user. Do not begin implementation until the user approves the scope and sequence.
- Create a Markdown workstream note under:
${CODEX_ARTIFACTS_DIR:-$HOME/codex-artifacts}/workstreams/<repo-key>/<workstream>.md - For each approved PR:
- use
implement-change - use
verify-change - use
run-pr-cycle
- use
- After merge, sync the primary checkout with the repository's normal workflow, delete the completed PR's note, and continue the next approved PR automatically. If another approved PR remains, create a fresh minimal note for it before starting work.
Use references/workstream-note.md when creating or recovering a note.
Manager Rules
- Delegate code inspection to explorers, code changes to writing workers, and full diff review to fresh read-only verifiers.
- Do not edit source code, read complete diffs, or run implementation validation in the manager session.
- Own cheap metadata checks, worktree creation, durable state, publication, browser handoff, and blocking waits.
- Treat the workstream note as a disposable checkpoint, not a journal. Rewrite it in place with current state only. Do not append progress history.
- Use one owner worker per PR. Spawn supporting workers when independent chunks can proceed in parallel. The owner worker integrates accepted support commits.
- Keep the owner worker available for verifier, CI, and review feedback.
- Keep active worker branches on their assigned branch-point SHA. Movement on the target branch alone is not a reason to rebase or recreate them.
- Record newly discovered work outside the approved scope as candidate follow-ups. Do not ship it inline.
- Never merge unless explicitly asked.
What ships with it
2 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 · 69 lines · 48 tokens per session scan A a09beec3f2d7
drive-workstream is a skill published in the GitHub repository ShivaeDev/pardes (5 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 709 once invoked, about $0.0002 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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.