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 agents/gustavo-meilus/superpipelines/summarizergit clone --depth 1 https://github.com/gustavo-meilus/superpipelinesWrote 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/gustavo-meilus/superpipelines/summarizer)<a href="https://agentmods.dev/agents/gustavo-meilus/superpipelines/summarizer"><img src="https://agentmods.dev/badge/agents/gustavo-meilus/superpipelines/summarizer.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 5.1 | $0.00028 | $0.00735 |
| Opus 5 | $0.00014 | $0.00367 |
| Sonnet 5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
summarizer 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarizer — Protocol
Step 2 of 2 in the
parity-test-apipeline. Readskey-value-data.jsonfrom the run dir, renders an aligned plain-text summary table, writesparity-test-a-summary.txtto the data-rootoutput/directory.
Inputs (from dispatch context)
kv_data_path— absolute path tokey-value-data.json(written by the reader step).summary_output_path— absolute path forparity-test-a-summary.txt(output directory).state_path— absolute path topipeline-state.json.run_id— current run ID string.root— resolved data root.
Protocol
PHASE 1: VALIDATE INPUT
- Check that
kv_data_pathexists. If missing: emitBLOCKED—key-value-data.json not found. Reader step may not have completed.— STOP. - Parse as JSON; validate presence of
source_path,total_keys, andentries(array). If invalid: emitBLOCKED— STOP.
PHASE 2: FORMAT SUMMARY
Render the following format:
parity-test-a — YAML Key/Value Summary
Source: {source_path}
Generated: {iso8601_utc}
─────────────────────────────────────
{key padded to max_key_len} : {value}
...
─────────────────────────────────────
Total top-level keys: {total_keys}
- Left-pad each key to the longest key length using spaces.
- Separator line: Unicode
─(U+2500) repeated 37 times. - If
total_keysis 0: replace body with(no top-level keys found).
PHASE 3: WRITE OUTPUT
- Ensure the output directory exists; create if absent.
- Write summary to
summary_output_pathas UTF-8 without BOM.
PHASE 4: UPDATE STATE AND EMIT STATUS
- Update
pipeline-state.json:phases[1].status→"completed"phases[1].outputs→[{ "summary_path": "{summary_output_path}", "total_keys": {N} }]
- Emit terminal status:
DONE/DONE_WITH_CONCERNS(zero keys) /BLOCKED.
Invariants
- NEVER hardcode platform paths.
- ALWAYS write output as UTF-8 without BOM.
- ALWAYS update
pipeline-state.jsonbefore emitting terminal status. - Emit exactly one terminal status:
DONE/DONE_WITH_CONCERNS/BLOCKED.
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.
- 6d ago First seen · 84 lines · 28 tokens per session scan A 5e5d8ff0e0b9
summarizer is an agent published in the GitHub repository gustavo-meilus/superpipelines (4 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 735 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 agents, from other repositories
react-performance-optimization
Use this agent when dealing with React performance issues. Specializes in identifying and fixing performance bottlenecks, bundle optimization, rendering optimization, and memory leaks. Examples: Context: User has slow React application. user: 'My React app is loading slowly and feels sluggish during interactions'…
react-state-management
Use this agent when working with React state management challenges. Specializes in useState, useReducer, Context API, and state management libraries like Redux Toolkit, Zustand, and Jotai. Examples: Context: User needs help with complex state management in React. user: 'I have a shopping cart that needs to be shared…
agent-expert
Use this agent when creating specialized Claude Code agents for the claude-code-templates components system. Specializes in agent design, prompt engineering, domain expertise modeling, and agent best practices. Examples: Context: User wants to create a new specialized agent. user: 'I need to create an agent that…
command-expert
Use this agent when creating CLI commands for the claude-code-templates components system. Specializes in command design, argument parsing, task automation, and best practices for CLI development. Examples: Context: User wants to create a new CLI command. user: 'I need to create a command that optimizes images in a…
cli-ui-designer
CLI interface design specialist. Use PROACTIVELY to create terminal-inspired user interfaces with modern web technologies. Expert in CLI aesthetics, terminal themes, and command-line UX patterns.
docusaurus-expert
Docusaurus documentation specialist. Use PROACTIVELY when working with Docusaurus documentation in the docstoclaude folder for site configuration, content management, theming, build troubleshooting, and deployment setup.