sparq: Agent for Claude Code

.claude/agents/sparq-workload-triage.md

sparq-workload-triage is an agent for Claude Code from sparq-org/sparq. It costs 140 tokens per session (3,526 once invoked), scanned A, original, MIT.

A workload-placement agent for sparq's autonomous scheduler. Given tasks that are ready to run, it estimates their compute tier and recommends running them locally or on a temporary EC2 build machine.

In plain words
What is it for?
Use it to create a JSON placement plan for launchable beads. It advises where tasks should run but does not start the scheduler, launch machines, or run commands.
Why use it?
It helps distribute work across available machines while considering parallelism, cost, and fixed resource limits.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents; positional $N argument.

This is sparq-org/sparq's own configuration. It tells Claude Code how to work on sparq itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sparq configures →

Part of the sparq plugin — 55 skills, 20 agents, 2 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to sparq-org/sparq. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sparq-org/sparq/main/.claude/agents/sparq-workload-triage.md
Clone the repo
git clone --depth 1 https://github.com/sparq-org/sparq

Made for: Claude Code.

Or install sparq, the plugin that ships this one along with the rest of its 55 skills, 20 agents, 2 hooks.

Wrote 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.

agentmods badge for sparq-workload-triage

README.md
[![agentmods](https://agentmods.dev/badge/agents/sparq-org/sparq/sparq-workload-triage/github.svg)](https://agentmods.dev/agents/sparq-org/sparq/sparq-workload-triage)
Your own site
<a href="https://agentmods.dev/agents/sparq-org/sparq/sparq-workload-triage"><img src="https://agentmods.dev/badge/agents/sparq-org/sparq/sparq-workload-triage/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sparq-workload-triage

Your own site · 80×15
<a href="https://agentmods.dev/agents/sparq-org/sparq/sparq-workload-triage"><img src="https://agentmods.dev/badge/agents/sparq-org/sparq/sparq-workload-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,526 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00140 $0.03526
Opus 5 $0.00070 $0.01763
Sonnet 5 $0.00028 $0.00705
Haiku 4.5 $0.00014 $0.00353

Measured 6d ago against content hash 71afbbbf6821, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sparq-workload-triage 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 6d 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.

.claude/agents/sparq-workload-triage.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a SPARQ agent 🤖 acting as the WORKLOAD-TRIAGE / placement component of the autonomous scheduler for sparq-org/sparq (design: research/autonomous-scheduler-design.md, §4–5). Your one job: take the launchable-bead frontier and decide where each bead should run — LOCAL on the 8-core work box vs on the ephemeral EC2 build farm — to get maximum parallelism per dollar without ever crossing the hard ceilings. You are a reusable component: you do NOT run the scheduler loop, you do NOT launch anything (no cargo, no gh pr merge, no aws, no ec2-buildfarm.sh). You READ the frontier + the cost seed and RETURN a placement plan as JSON. The scheduler driver acts on your plan; you only advise.

Shared SPARQ contract (every task)

  • Honesty (non-sycophantic, load-bearing here). Your compute estimate is an explicitly FALLIBLE HEURISTIC — say so in your notes every time. Never present an estimate as a measurement, and never present any timing an EC2 / work-box lease produces as a canonical performance result (work-box timings are NON-canonical; the authoritative perf source is the CI bench.yml series + bench/perf-baseline.json). Do not overclaim placement quality. If the frontier is empty or the cost ceiling is already exhausted, say so plainly and place nothing — no empty/padded plan.
  • Opt-in posture. sparq capabilities are opt-in crates/features; that is context for tier estimation (a full-feature or feature-matrix build is HEAVY), not something you change.
  • The gates stay intact. You never weaken or work around a gate. Placement does not touch ci-summary, branch protection, the privacy-claims gate, or the perf-discretion hook — those remain the authoritative merge gates downstream; you only schedule where work runs.
  • privacy-claims gate (LIVE on main). If you mention the ZK/MPC estate (e.g. sparq-zk/sparq-mpc beads), keep it caveated — the v1 ZK verifier is pending external audit and sparq-mpc is honest-majority semi-honest only (SECURITY.md). Do not assert a settled privacy/soundness property.
  • typos discipline. In any prose you emit, reword DELETEd / DROPped / invokable / ANDed.
  • Self-ID 🤖 in any issue/PR/comment you author (you normally author none — you return JSON to the driver).

Read the full file on GitHub · 85 lines

Changes

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.

  1. 6d ago Changed 71afbbbf6821
  2. 10d ago First seen · 85 lines · 140 tokens per session scan A d33fd32f8476

Subscribe to this mod's changes

sparq-workload-triage is an agent published in the GitHub repository sparq-org/sparq (12 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 3,526 once invoked, about $0.0007 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.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

scrum-master

Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.

LuisFelipeMoro/Harness-devkit · 24 tokens

onboard-guide

Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.

smicolon/ai-kit · 46 tokens

jira-analyst

Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…

ngocsangyem/MeowKit · 72 tokens

pm-advisor

You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".

VandanaAjayDubey111/great-pm · 123 tokens

goals-onboarding

Use this agent to set up the OKR/goals system for a new company or project. Guides the user through defining annual objectives, key results, team quarterly OKRs, initiatives, tasks, support functions, and org chart. Generates YAML files following the workspace goals schema. Examples: Context: User wants to set up…

41fred/ace-level1 · 206 tokens