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 agentsight-system-frictiongit 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/agentsight-system-friction)<a href="https://agentmods.dev/skills/eunomia-bpf/agentsight/agentsight-system-friction"><img src="https://agentmods.dev/badge/skills/eunomia-bpf/agentsight/agentsight-system-friction/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/agentsight-system-friction"><img src="https://agentmods.dev/badge/skills/eunomia-bpf/agentsight/agentsight-system-friction.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 | $0.00019 | $0.01017 |
| Opus 5 | $0.00010 | $0.00508 |
| Sonnet 5 | $0.00004 | $0.00203 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
agentsight-system-friction 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentSight System Friction
Goal
Use AgentSight evidence to recommend operational improvements for agent runs: resource budgets, retry behavior, service lifecycle, cleanup/recovery, network binding, file/log hygiene, tool/MCP behavior checks, and capture quality. Use system metadata, not raw conversation payloads. Default reports should help an owner improve the next run using changes to existing commands, configs, hooks, and workflows; they should not expose the local machine's private identifiers.
Workflow
-
Privacy mode: Default to
team-share. Readreferences/privacy-modes.mdbefore including paths, commands, hosts, headers, or secret-adjacent details. For HTML reports and examples, use reader-safe summaries: path categories, command categories, host categories, port classes, session categories, resource windows, source types, counts, durations, and operating decisions. Exact local identifiers belong only in private-debug work requested by the user. -
Route evidence to reference docs:
- Sources and limits:
references/agentsight-sources.md - Evidence model:
references/system-evidence-model.md - Improvement classes:
references/operational-improvement-classes.md - Friction taxonomy:
references/system-friction-taxonomy.md - Correlation summary:
references/handoff-contract.md - Output shapes:
references/report-shapes.md - Examples:
references/example-patterns.md
- Sources and limits:
-
Build system facts:
- Summarize session/process correlation, command exits, long-running processes, file activity, network endpoints, resource outliers.
- Prefer timestamps, statuses, counts, durations, and categories over LLM payload columns.
- Distinguish monitor aggregates from record-level evidence.
- Preserve join keys internally for later correlation, but render category labels in reader-facing HTML by default.
- If user intent is needed, state that it requires
agent-interaction-insightsor a user-provided summary.
If the user provides both system data and raw interaction logs, analyze only system evidence here. Route raw conversation data to
agent-interaction-insights.
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 337 B
- references/agentsight-sources.md 1.4 KB
- references/example-patterns.md 2.3 KB
- references/handoff-contract.md 1011 B
- references/operational-improvement-classes.md 2.2 KB
- references/privacy-modes.md 789 B
- references/report-shapes.md 2.8 KB
- references/system-evidence-model.md 1.4 KB
- references/system-friction-taxonomy.md 1.6 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.
- 10d ago First seen · 78 lines · 19 tokens per session scan A 87e82aa70bb2
agentsight-system-friction is a skill published in the GitHub repository eunomia-bpf/agentsight (678 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 1,017 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
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
langbot-plugin-dev
Develop, debug, and test LangBot plugins. Use when creating new LangBot plugins, fixing plugin bugs, setting up a LangBot test environment, or testing plugins via WebSocket. Covers plugin component architecture (EventListener, Command, Tool), the plugin SDK API (invokellm, getllmmodels, sendmessage, plugin storage)…
code-task
PREFERRED way to change code in a REAL repository: fix a GitHub issue, fix a bug, add/implement a function or feature, or make any edit to a project the user names by a filesystem path (e.g. /tmp/foo, /code/bar) or a git URL. Clones the repo, runs an OpenSquilla agent on the host to make the change on a task branch…
stack-trace-js-probe
Internal helper for meta-stack-trace-investigator. Use when a JavaScript or TypeScript stack trace needs npm/node/tsc-specific checks, reproduction guidance, and patch targets.
stack-trace-generic-probe
Internal helper for meta-stack-trace-investigator. Use when a stack trace language is unknown and the workflow needs language-neutral failure-contract checks, reproducer guidance, and patch targets.