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 skills/generous-corp/pulp/friction-reportnpx skills add Generous-Corp/pulp --skill friction-reportgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/generous-corp/pulp/friction-report)<a href="https://agentmods.dev/skills/generous-corp/pulp/friction-report"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/friction-report.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 | $0.00102 | $0.03879 |
| Opus 5 | $0.00051 | $0.01939 |
| Sonnet 5 | $0.00020 | $0.00776 |
| Haiku 4.5 | $0.00010 | $0.00388 |
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 today.
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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Friction report
The point: most friction is paid twice — once when it happens, and again every time it happens to someone else. This skill pays it once by writing it down in a form the next agent can act on.
The trap this exists to avoid: an agent fixes a conflicting PR, feels productive, and never asks why the PR conflicted. The rebase takes ten minutes and the root cause survives to bite thirty more PRs. A fix without a report is a rerun waiting to happen.
When to invoke
- A PR is conflicting, red, or stuck, and it is not obvious why.
- You just did something manual that you suspect you will do again.
- The same class of failure has appeared twice. (Twice is a pattern. Once is weather.)
- A gate, hook, or workflow blocked something it should not have — or waved through something it should not have.
- Daniel says a version of "why does this keep happening?"
Do NOT invoke for a genuine one-off (a typo, a flaky network call). The bar is: would this bite someone else?
⛔ STEP ZERO — CONSTRAINT DISCOVERY (mandatory, no exceptions)
This step exists because the skill failed without it. Its first real use produced a confident, well-evidenced, actively dangerous proposal — it identified a gate as a bug and recommended removing it. But the repo documented why that gate existed: it was added after a release silently failed to ship, and removing it would have reintroduced exactly that failure. The evidence was solid; the proposal was still wrong, because it never asked what the gate was protecting.
Most "obviously wrong" designs are scar tissue. Find the scar before you cut.
Do every check below. Write the answers into the report. A proposal without these sections is invalid.
0.1 — What is this repo's toolchain? (DETECT, never assume)
Do not hardcode. Daniel uses Shipyard and tartci often, but not everywhere, and other repos differ. Detect:
ls .shipyard/config.toml # Shipyard? which gates/targets?
ls .tartci* tools/tartci* # tartci? self-hosted runners?
ls .github/workflows/ # plain GitHub Actions? which are REQUIRED?
ghapp api repos/{owner}/{repo}/branches/main/protection -q '.required_status_checks.contexts'
ghapp api repos/{owner}/{repo} -q '.allow_squash_merge, .allow_merge_commit, .allow_rebase_merge'
git log --oneline -5 origin/main # squash? merge commits? who pushes to main?
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.
- today First seen · 339 lines · 102 tokens per session scan A 27d99f145d80
friction-report is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 3,879 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…