What is friction-report?

A command that reports where the exit-status guard blocked actions in your local Claude Code session transcripts. It reads existing records and adds no telemetry.

Reviewing guard decisions, counting caught false greens, and deciding whether the most common rule reflects a user habit or a registry defect.

It helps identify repeated blocked commands without treating missing records as successful runs or calling the result a true friction rate.

friction-report — Command for Claude Code by karlkfi/claude-bouncer

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add karlkfi/claude-bouncer

Claude Code

/plugin install exit-status-guard

Made for: Claude Code.

Or install exit-status-guard, the plugin that ships this one along with the rest of its 1 command.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/karlkfi/claude-bouncer/friction-report/github.svg)](https://agentmods.dev/commands/karlkfi/claude-bouncer/friction-report)

Your own site

<a href="https://agentmods.dev/commands/karlkfi/claude-bouncer/friction-report"><img src="https://agentmods.dev/badge/commands/karlkfi/claude-bouncer/friction-report/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/karlkfi/claude-bouncer/friction-report"><img src="https://agentmods.dev/badge/commands/karlkfi/claude-bouncer/friction-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 211 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00018	$0.00211
Opus 5.5	$0.00007	$0.00084
Sonnet 5.5	$0.00004	$0.00042
Haiku 4.5	$0.00002	$0.00021

Measured 2mo ago against content hash bfd50160e79a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

plugins/exit-status-guard/commands/friction-report.md · 19 lines

What it actually says

The exit-status-guard friction report below is generated by re-reading the hook decisions Claude Code already recorded in your local session transcripts (it adds no telemetry — see PRIVACY.md). Show it to me verbatim, then add at most one sentence naming the rule that fires most and whether it looks like a habit worth fixing or a defect in the registry.

Every exit-status-guard verdict is a deny, and there is no denominator: the guard emits nothing when it has no objection, so silent runs leave no record. Read the counts as "false greens caught", not as a friction rate. Do not edit any files.

!python3 "${CLAUDE_PLUGIN_ROOT}/scripts/friction-report.py" $ARGUMENTS

Changes

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.

2mo ago First seen · 19 lines · 18 tokens per session scan A bfd50160e79a

Subscribe to this mod's changes

friction-report is a command published in the GitHub repository karlkfi/claude-bouncer (13 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 211 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Analytics and metrics Claude Code agentic-ai ai-agents anthropic bash claude-code-hooks

friction-report next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
friction-reportkarlkfi/claude-bouncer	Command	13	yesterday	MIT	A	18	Claude Code
cost-optimizewshobson/agents	Command	42k	2d ago	MIT	A	26	Claude Code
refactor-cleanwshobson/agents	Command	42k	2d ago	MIT	A	26	Claude Code
deps-auditwshobson/agents	Command	42k	2d ago	MIT	A	23	Claude Code
spreadsheet-auditintellegix/intellegix-code-agent-toolkit	Command	57	6d ago	MIT	A	0	Claude Code
research-perplexityintellegix/intellegix-code-agent-toolkit	Command	57	6d ago	MIT	A	0	Claude Code
handoffintellegix/intellegix-code-agent-toolkit	Command	57	6d ago	MIT	A	0	Claude Code