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 skills add eunomia-bpf/agentsight --skill agentpprof-flamegraphgit clone --depth 1 https://github.com/eunomia-bpf/agentsightWrote 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/skills/eunomia-bpf/agentsight/agentpprof-flamegraph)<a href="https://agentmods.dev/skills/eunomia-bpf/agentsight/agentpprof-flamegraph"><img src="https://agentmods.dev/badge/skills/eunomia-bpf/agentsight/agentpprof-flamegraph.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 | $0.00026 | $0.02352 |
| Opus 5 | $0.00013 | $0.01176 |
| Sonnet 5 | $0.00005 | $0.00470 |
| Haiku 4.5 | $0.00003 | $0.00235 |
Grade A, and why
agentpprof-flamegraph 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 7d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentpprof Flamegraph Generation
Goal
Generate meaningful flamegraphs from local Codex/Claude Code sessions by iteratively developing tag rules that achieve high prompt coverage.
Workflow
1. Initial Discovery
Run agentpprof without rules to see diagnostics:
agentpprof \
--project-root /path/to/project \
--view tokens \
-o initial.json \
--format json \
--include-previews
The output includes:
tagging.total_prompts: total prompts foundtagging.unmatched_prompts: prompts without tagstagging.unmatched_samples: sample unmatched prompts (up to 20)tagging.hint: suggested next step
2. Analyze Unmatched Prompts
Look at unmatched_samples to identify patterns:
- Common keywords or phrases
- Chinese/English patterns
- Action types (review, debug, git, etc.)
- Project-specific terminology
3. Develop Tag Rules
Add --tag-rule arguments iteratively:
agentpprof \
--project-root /path/to/project \
--tag-rule 'prompt:review=(?i)review|审核|check' \
--tag-rule 'prompt:debug=(?i)fix|bug|error|broken' \
--tag-rule 'prompt:git=(?i)commit|push|pull|git' \
--view tokens \
-o iter1.folded
Rule syntax: KIND:TAG=REGEX
- KIND:
prompt,session,llm, orall - TAG: lowercase word, 3-12 letters (semantic, not vague)
- REGEX: case-insensitive patterns with
(?i)
Avoid vague tags like task, work, misc, thing, stuff, other — they don't convey semantic meaning and won't aggregate well. Use specific tags like debug, review, paper, naming that describe the activity.
Never use catch-all rules like prompt:misc=. or llm:other=. — they defeat the purpose of semantic tagging by lumping everything together. If you can't classify an item, leave it unmatched and add more specific rules.
Never use placeholder tags like llm:placeholder, llm:response, prompt:other — they indicate that the tagging rules are incomplete. If you see placeholder tags dominating the distribution, investigate why the content isn't being classified properly. Common causes:
- Parser limitations (e.g.,
"claude response"preview means the actual response content wasn't extracted) - Rules ordered incorrectly (more specific rules should come before general ones)
- Missing rules for common patterns
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.
- 7d ago First seen · 248 lines · 26 tokens per session scan A 96d2f9ae3920
agentpprof-flamegraph is a skill published in the GitHub repository eunomia-bpf/agentsight (671 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 2,352 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 2026-08-30.
Other skills, from other repositories
prometheus
Prometheus monitoring expert for PromQL, alerting rules, Grafana dashboards, and observability.
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
skill-creator-linter
Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.
paper-abstract-author
Write the abstract after the paper body has been revised, using the final claims and evidence.
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.