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/runnithan/claudex-setup/pre-aggregate-profiling-data-for-agentsgit clone --depth 1 https://github.com/runnithan/claudex-setupWrote 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/runnithan/claudex-setup/pre-aggregate-profiling-data-for-agents)<a href="https://agentmods.dev/agents/runnithan/claudex-setup/pre-aggregate-profiling-data-for-agents"><img src="https://agentmods.dev/badge/agents/runnithan/claudex-setup/pre-aggregate-profiling-data-for-agents.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 | $0.00000 | $0.00299 |
| Opus 5 | $0.00000 | $0.00150 |
| Sonnet 5 | $0.00000 | $0.00060 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
pre-aggregate-profiling-data-for-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 4d 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
Pre-Aggregate Profiling/Runtime Data Before Handing It to an Agent
TL;DR
When you want a coding agent to fix slow code, don't dump raw profiler output, give it a single tool that aggregates samples (frequencies, percentiles) into an analyzed view, because LLMs are bad at doing those computations themselves.
Why it matters
Agents see the caller code but not the runtime characteristics of callees, so they guess and pick the wrong hotspot. Raw flamegraph output forces the model to do statistical aggregation it's poorly suited for; a pre-analyzed view (e.g. '~22% CPU in this function') lets it correctly localize the bottleneck.
How to apply
When wiring performance/observability tooling for an agent: expose at most a handful of tools (ideally one); have the tool itself compute frequencies and percentile durations and present a consumable summary, not raw samples; supply runtime data alongside the source; and be specific about which path is slow.
Related
[[cli-tools-over-mcp-for-tokens]], [[design-cli-help-for-agents]]
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.
- 4d ago First seen · 29 lines · 0 tokens per session scan A 8dc9d85b12b1
pre-aggregate-profiling-data-for-agents is an agent published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 299 tokens. 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
engram-assessor
Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review audits. Deliberately blind to the tutoring dialogue — receives only items and rubrics, returns receipt JSON.
engram-curriculum-architect
Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic or restructuring one. Returns strict JSON for engram.py add-topic.
information-architect
Adversarial information architect who assumes the current documentation is harder to find, orient in, and comprehend than it needs to be. Audits READMEs, API docs, plugin docs, ADR collections, tutorials, and reference content against established IA practice — the four IA systems (organization, labeling, navigation…
engram-artifact-smith
Builds interactive HTML explorables for Engram threshold concepts under the binding Explorable Contract. Use after encoding a threshold node, or to re-encode a repeatedly-lapsing node visually.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
knowledge-extractor
Deep-analysis agent spawned by /crystallize. Reads session logs and lessons.md, clusters patterns with ≥3 occurrences, and writes draft skill files to skills/{domain}/SKILL.md.