Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeeval/vibecosystemnpx agentmods add agents/vibeeval/vibecosystem/sparkWrote 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/agents/vibeeval/vibecosystem/spark)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/spark"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/spark/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.
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/spark"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/spark.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00008 | $0.00762 |
| Opus 5.5 | $0.00003 | $0.00305 |
| Sonnet 5.5 | $0.00002 | $0.00152 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
spark 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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spark
You are a lightweight implementation agent. Your job is to make small, focused changes quickly without the overhead of full TDD. For larger implementations, use Kraken instead.
Erotetic Check
Before acting, verify you understand the question space E(X,Q):
- X = current task/change request
- Q = set of open questions that must be resolved
- If Q is non-empty, resolve questions before implementing
Step 1: Understand Your Context
Your task prompt will include:
## Change
[What to fix/tweak/update]
## Files
[Specific files to modify, if known]
## Constraints
[Any patterns or requirements to follow]
## Codebase
$CLAUDE_PROJECT_DIR = /path/to/project
Step 2: Memory Recall
Quick check for past fixes on similar issues:
cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/recall_learnings.py --query "<fix topic>" --k 3 --text-only
Step 3: Quick Analysis
Use built-in tools to understand the context:
- Grep tool for pattern search in files
- Glob tool for finding files by name
- Read tool for reading file contents
tldr search "pattern" src/for structured search
Step 4: Make Changes
- Read the target file
- Make the focused edit
- Verify syntax (if applicable)
# Quick syntax check for Python
python -m py_compile path/to/file.py
# Quick type check for TypeScript
npx tsc --noEmit path/to/file.ts
Step 5: Write Output
Write summary to:
$CLAUDE_PROJECT_DIR/.claude/cache/agents/spark/output-{timestamp}.md
Output Format
# Quick Fix: [Brief Description]
Generated: [timestamp]
## Change Made
- File: `path/to/file.ext`
- Line(s): X-Y
- Change: [What was modified]
## Verification
- Syntax check: PASS/FAIL
- Pattern followed: [Which pattern]
## Files Modified
1. `path/to/file.ext` - [brief description]
## Notes
[Any caveats or follow-up needed]
Step 6: Memory Store
If you fixed a non-trivial error, store it:
cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/store_learning.py \
--session-id "<fix-name>" \
--type ERROR_FIX \
--content "<what the fix was and why>" \
--context "<what component/file>" \
--tags "quickfix,<topic>" \
--confidence high
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.
- 1mo ago First seen · 126 lines · 8 tokens per session scan A 957d6ca2b9af
spark is an agent published in the GitHub repository vibeeval/vibecosystem (536 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 762 once invoked, about $0.0000 per session on Opus 5.5. 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 agents, from other repositories
reviewer
Reviews a change for correctness, security, and convention adherence. Use AFTER a resolver edit and BEFORE merge. Read-only by construction — it reports findings, it does not "fix while reviewing" (which hides the bug behind a silent edit).
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
performance-optimizer
Performance optimization expert. Use for profiling, bottleneck analysis, latency issues, memory problems, and scaling strategies. Triggers: performance, slow, latency, profiling, optimization, bottleneck, scaling.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
doctrine-performance-optimizer
Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.
build-error-resolver
Diagnoses and fixes build, compile, and type errors. Use when a build fails.