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 agent-interaction-insightsgit 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/agent-interaction-insights)<a href="https://agentmods.dev/skills/eunomia-bpf/agentsight/agent-interaction-insights"><img src="https://agentmods.dev/badge/skills/eunomia-bpf/agentsight/agent-interaction-insights/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/skills/eunomia-bpf/agentsight/agent-interaction-insights"><img src="https://agentmods.dev/badge/skills/eunomia-bpf/agentsight/agent-interaction-insights.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.00870 |
| Opus 5 | $0.00011 | $0.00435 |
| Sonnet 5 | $0.00004 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
agent-interaction-insights 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 9d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Interaction Insights
Goal
Turn agent conversation and trace evidence into concrete next-run improvements: prompts, AGENTS.md/CLAUDE.md, workflow, validation rules, tool policy, or task routing. Lead with what should change; use evidence to justify the change. Default reports should read like decision material for an agent owner.
Workflow
-
Privacy mode: Default to
team-share. Readreferences/privacy-modes.mdbefore extracting prompt/response/path/command/header/secret-adjacent data. For HTML reports and examples, use reader-safe summaries: short task/claim summaries, field categories, time ranges, counts, statuses, and analysis boundaries. Exact local identifiers belong only in private-debug work requested by the user. -
Classify the question:
improve-collaboration: reduce corrections, clarify framing, improve AGENTS.md/CLAUDE.md.improve-trust: make summaries and validation claims reliable.reduce-waste: stop loops, retry churn, token/time waste.improve-workflow: decide which instructions, checks, evals, policies, or workflow gates should change.compare-fit: compare agents, models, prompts, or task classes.
-
Route evidence to reference docs:
- Sources:
references/data-source-routing.md - Improvement classes:
references/improvement-classes.md - Evidence model:
references/common-evidence-model.md - Friction taxonomy:
references/friction-taxonomy.md - System summary input:
references/handoff-contract.md - Output shapes:
references/report-shapes.md - Examples:
references/example-patterns.md
If the user provides both interaction logs and AgentSight/system data, analyze only interaction evidence here. Consume already summarized system findings as compact context; route raw AgentSight data to
agentsight-system-friction. - Sources:
-
Build facts:
- Map records into sessions, messages, LLM calls, tool attempts, validation claims, and user signals.
- Extract minimal fields; distinguish observed from inferred.
- Note when transcripts cannot prove process/file/network side effects.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 274 B
- references/common-evidence-model.md 1.5 KB
- references/data-source-routing.md 1.9 KB
- references/example-patterns.md 1.8 KB
- references/friction-taxonomy.md 2.1 KB
- references/handoff-contract.md 923 B
- references/improvement-classes.md 1.7 KB
- references/privacy-modes.md 956 B
- references/report-shapes.md 2.7 KB
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.
- 9d ago First seen · 79 lines · 22 tokens per session scan A 71ee344adcf1
agent-interaction-insights is a skill published in the GitHub repository eunomia-bpf/agentsight (676 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 870 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…
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
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.