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 commands/aneja5/forge-skills/parallelgit clone --depth 1 https://github.com/aneja5/forge-skillsWhat 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 | $0.00019 | $0.00188 |
| Opus 5 | $0.00010 | $0.00094 |
| Sonnet 5 | $0.00004 | $0.00038 |
| Haiku 4.5 | $0.00002 | $0.00019 |
Grade A, and why
parallel 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.
What it actually says
Invoke the forge-skills:parallel-execution-strategy skill.
Read .forge/tasks.yaml. Identify dependency-free groups — both depends_on AND files lists must not intersect.
Build a file-conflict matrix per group. Any row with two ✏️ marks is a conflict — split, sequence, or designate a primary.
Assign one branch per task (task/T-XXX-description), all based off main.
Define PR sequencing and merge order before dispatch. Lowest-blast-radius first; tasks that mutate shared types/contracts land first so others rebase on them.
Each agent runs in its own git worktree — never share.
Define integration-test gate between every merge and between groups.
After writing: "Parallel plan written to .forge/parallel-plan.md. Dispatch only after the plan is signed off."
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 · 15 lines · 19 tokens per session scan A b8346264f8ab
parallel is a command published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 188 once invoked, about $0.0001 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 commands, from other repositories
setup:existing
Add Claude Code framework to an existing project with auto-detection.
multi-agent-optimize
The Multi-Agent Optimization Tool is an advanced AI-driven framework designed to holistically improve system performance through intelligent, coordinated agent-based optimization. Leveraging cutting-edge AI orchestration techniques, this tool provides a comprehensive approach to performance engineering across multiple…
ship-an-mcp-server
Workflow recipe — make your product agent-usable by chaining 4 skills, spec to pricing.
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…
loop-forge
Turn a one-line repetitive task into a reusable, self-guarding slash command (loop-forge).
ox-session-review
Command "ox-session-review" from sageox/ox, covering failure-mode watch-list (read first), from the ledger root. should print 0, phase 1 — scan & score (read-only), quality buckets (first match wins) and removal candidates.