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/phuonghx/aim-cli/parallel-agentsnpx skills add phuonghx/aim-cli --skill parallel-agentsgit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00089 | $0.01347 |
| Opus 5 | $0.00044 | $0.00674 |
| Sonnet 5 | $0.00018 | $0.00269 |
| Haiku 4.5 | $0.00009 | $0.00135 |
Grade A, and why
parallel-agents 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Agents
This skill is about marshalling specialist agents through the platform's own Agent tool. Everything stays inside one session and under the host's control — no external scripts, no separate processes to babysit.
Is Orchestration The Right Call
Reach for it when:
- The work genuinely spans several areas of expertise.
- You want code looked at through security, performance, and quality lenses at once.
- A review needs to cover architecture, security, and testing together.
- A feature touches backend, frontend, and the data layer all at once.
Leave it alone when:
- The task sits squarely in one domain.
- It's a small fix or a quick edit.
- A single agent would clearly suffice.
Calling Agents
A single specialist:
Have the security-auditor review the authentication flow.
A chain, one after another:
Start with explorer-agent to map the project layout.
Then backend-specialist to review the API surface.
Finally test-engineer to find the coverage gaps.
Passing findings down the chain:
Have frontend-specialist analyze the React components,
then hand those findings to test-engineer to write matching tests.
Picking up where one left off:
Resume agent [agentId] and continue with the extra requirements.
Three Orchestration Shapes
Whole-codebase review
explorer-agent → domain specialists → synthesis
1. explorer-agent maps the structure
2. security-auditor judges the security posture
3. backend-specialist weighs API quality
4. frontend-specialist reviews the UI patterns
5. test-engineer measures coverage
6. fold it all into one report
Reviewing a change
affected specialists → test-engineer
1. work out which domains the change touches
2. bring in just those specialists
3. test-engineer confirms the change holds
4. consolidate the recommendations
Security audit
security-auditor → penetration-tester → synthesis
1. security-auditor does the config and code review
2. penetration-tester probes for live vulnerabilities
3. synthesize with a prioritized fix list
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 · 157 lines · 89 tokens per session scan A 8a72597e23a7
parallel-agents is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 1,347 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
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).