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/aneja5/forge-skills/parallel-execution-strategynpx skills add aneja5/forge-skills --skill parallel-execution-strategygit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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/aneja5/forge-skills/parallel-execution-strategy)<a href="https://agentmods.dev/skills/aneja5/forge-skills/parallel-execution-strategy"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/parallel-execution-strategy.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 | $0.00059 | $0.01874 |
| Opus 5 | $0.00030 | $0.00937 |
| Sonnet 5 | $0.00012 | $0.00375 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
parallel-execution-strategy 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 yesterday.
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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Execution Strategy
Overview
Plan parallel agent execution before dispatching — so two agents never edit the same file, so integration is verified between merges, and so the merge order is fixed in advance. Output is .forge/parallel-plan.md — dependency-free task groups, file-conflict risk per group, branching strategy (one branch per task), PR sequencing, agent isolation (separate worktrees), and integration-test cadence. Pairs with planning-and-task-breakdown (the source tasks.yaml) and git-workflow (the branch and PR mechanics).
When to Use
.forge/tasks.yamlhas 3+ tasks marked ready and they appear independent- Multiple engineers or agents are about to start work in the same week
- A prior parallel run caused merge conflicts at the end and the team wants a better plan
- A sprint is about to begin and capacity is "split N ways"
When NOT to Use
- Only one task is ready — sequential is correct
- Tasks form a strict dependency chain — sequential is correct
- The team is two people working on the same file all day — coordinate live, no plan needed
Common Rationalizations
| Thought | Reality |
|---|---|
| "We'll just merge at the end" | Merge conflicts at the end compound. Each agent's mental model of the codebase has diverged. Resolving 5 PRs simultaneously is 5x more work than resolving them in sequence. |
| "Agents can share files, git will sort it out" | Git produces unresolvable conflicts when two agents edit the same function with no shared context. The "resolution" is one engineer hand-merging both versions. |
| "We don't need integration tests between merges" | Silent integration failures accumulate. By PR 5, nobody knows which of the previous 4 PRs introduced the bug. |
| "Sequential is safer than parallel" | Sequential wastes parallelizable work. The cost of planning beats the cost of unparallelized execution. |
| "We'll figure out merge order as we go" | First-merger-wins creates rebase chaos. Set the order at dispatch time. |
| "One worktree is fine, agents can take turns" | Agents don't "take turns" — they overwrite each other's working tree state. Each agent needs isolation. |
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.
- yesterday First seen · 165 lines · 59 tokens per session scan A b924eb3f5e38
parallel-execution-strategy is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,874 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 2026-09-03.
Other skills, from other repositories
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
implement
Use when implementing a spec or GitHub ticket in this checkout.
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
tdd
Use when implementing features or bug fixes test-first.