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 aurorascharff/agent-friction-skill --skill passivegit clone --depth 1 https://github.com/aurorascharff/agent-friction-skillWrote 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/aurorascharff/agent-friction-skill/passive)<a href="https://agentmods.dev/skills/aurorascharff/agent-friction-skill/passive"><img src="https://agentmods.dev/badge/skills/aurorascharff/agent-friction-skill/passive.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 | $0.00047 | $0.02118 |
| Opus 5 | $0.00023 | $0.01059 |
| Sonnet 5 | $0.00009 | $0.00424 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
friction-report 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
friction-report
End-of-session friction reporter. Scans the conversation you just had for build failures, doc gaps, SDK surprises, misleading errors, and training-data fallbacks. If anything worth reporting was found, drafts a structured report for human review. If the session was clean, exits silently.
No buffer, no per-turn tracking, no initialization step. Your conversation history is the source of truth.
When to run
- At the end of a dev session — when the user says "done", "thanks", "that's it", or when the task is clearly complete
- When the user explicitly asks: "report your friction", "what friction did you hit?", "give me the friction report"
- When the harness invokes this skill by name
If the user explicitly invoked the friction-log skill during this session, do not run — that skill already produced a detailed log.
Payload
Matches the same schema the visualizer validates. All top-level fields:
schema_version— always1.framework— what was being used (e.g.next,vite,remix). Required.framework_version— exact version frompackage.jsonor CLI. Required.summary— one sentence, biggest pain point. No user prompt verbatim, no code. Required.model— your model id (e.g.claude-opus-4-7). Optional.harness— what you're running in (e.g.VS Code agent,Claude Code). Optional.scaffold_flags— flags used when scaffolding (e.g.["--typescript", "--app"]). Optional.build_count— how many builds ran during the session. Optional.cumulative_build_ms— total build time in ms. Optional.friction_points[]— each one has:severity:red(blocked/broken) oryellow(extra steps/guesswork). Do NOT include greens.title: one-line description, ≤200 chars.expected: what you thought would happen. Strongly recommended, not optional in practice — without it, the report can't be reproduced.actual: what actually happened. Strongly recommended, include the full causal chain when one symptom was caused by a separate upstream mistake (e.g. "page omitted Suspense because feature pre-wrapped its own, contradicting the architecture skill").resolution: how it was fixed, or "unresolved". Strongly recommended.source_tag: one ofagents.md,docs,url,web search,training data,error output,sandbox,skill.file_kind: what kind of file (e.g.route handler,next.config). Never an absolute path. Optional.redacted_snippet: one redacted line of error output, ≤200 chars. Optional.
action_items[]— each one has:bucket:docs,framework, orresearch.title: what should be fixed or investigated.context: the specific friction that led to this item, including upstream causes when relevant.
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 · 160 lines · 47 tokens per session scan A 94c6a6c861b2
friction-report is a skill published in the GitHub repository aurorascharff/agent-friction-skill (23 stars, last pushed 7d ago), licensed MIT. It adds 47 tokens to every session and 2,118 once invoked, about $0.0002 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.