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/gabrieldabbah/genesis/parallel-worknpx skills add gabrieldabbah/genesis --skill parallel-workgit clone --depth 1 https://github.com/gabrieldabbah/genesisWrote 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/gabrieldabbah/genesis/parallel-work)<a href="https://agentmods.dev/skills/gabrieldabbah/genesis/parallel-work"><img src="https://agentmods.dev/badge/skills/gabrieldabbah/genesis/parallel-work.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00075 | $0.01205 |
| Opus 5 | $0.00037 | $0.00602 |
| Sonnet 5 | $0.00015 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
parallel-work 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 4d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel session mode
Another Claude session is working in this repository right now. The working tree, the running processes, the git index, and whatever the tests touch are all shared. Assume every one of them has an owner other than you.
Rules
- No git writes. Do not commit, push, stage, stash, checkout, reset, restore, merge, rebase, or switch branches. Finish the work, leave it uncommitted, and say so. The owner commits.
- Diffs you did not make are not yours.
git statuswill show another session's in-flight edits. Never revert, clean, or "tidy" them. If a file you are editing changes under you, re-read it and merge your change on top — do not overwrite. - Stay inside the requested scope. Touch only the files the request names or strictly requires. No drive-by refactors and no reformatting. A problem in a file you are not already editing is named in the report and never fixed here — it probably belongs to another session's in-flight work, and an unrelated file you edit is a file you are colliding with someone on. A defect in a file you are already changing stays yours to fix, in this mode as in every other.
- Do not kill processes. No
pkill,killall, port sweeps, or container teardowns — the dev server, test run, or database you would kill probably belongs to the other session. Kill only a PID you spawned this turn and captured yourself. Leftovers you did not spawn get reported, not killed.
Verifying without corrupting anyone
A test run is not a read. Most suites write: they insert fixtures, truncate or reset a database, bind a fixed port, populate a cache, or write to a shared build directory. Run one while another session is mid-run and you corrupt both — and that is worse than a wasted run, because the wreckage looks like real findings. Rows vanish mid-assertion, a port refuses to bind, a snapshot mismatches, a count comes back one too high. Whoever reads that output then debugs a bug that does not exist. Both sessions lose, and the false result is the expensive part.
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.
- 4d ago First seen · 82 lines · 75 tokens per session scan A d72f77eb2110
parallel-work is a skill published in the GitHub repository gabrieldabbah/genesis (4 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,205 once invoked, about $0.0004 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
fleet
Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave in isolated worktrees, collects discoveries, shares context between waves. Use when work decomposes into 3+ independent streams that can run simultaneously.
setup
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.
daemon
Continuous autonomous operation mode. Keeps campaigns running 24/7 by chaining Claude Code sessions via RemoteTrigger. Each session picks up from the campaign's continuation state, works until context runs low or the phase completes, then schedules the next session. Auto-stops on campaign completion or budget…
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…