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.
/plugin marketplace add karlkfi/claude-bouncer/plugin install workspace-guardWrote 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/karlkfi/claude-bouncer/reduce-workspace-guard-prompts)<a href="https://agentmods.dev/skills/karlkfi/claude-bouncer/reduce-workspace-guard-prompts"><img src="https://agentmods.dev/badge/skills/karlkfi/claude-bouncer/reduce-workspace-guard-prompts/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/karlkfi/claude-bouncer/reduce-workspace-guard-prompts"><img src="https://agentmods.dev/badge/skills/karlkfi/claude-bouncer/reduce-workspace-guard-prompts.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00069 | $0.01670 |
| Opus 5 | $0.00034 | $0.00835 |
| Sonnet 5 | $0.00014 | $0.00334 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
reduce-workspace-guard-prompts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reducing workspace-guard prompts
workspace-guard is a PreToolUse hook that prompts before a guarded bash file
command (grep, sed, awk, jq, cat, head, tail, cp, mv, rm,
tee, dd, and friends) reads or writes a path outside the project root
($CLAUDE_PROJECT_DIR). In-root reads and pure pipelines run silently. So a
flood of prompts means commands keep resolving paths outside the root — usually
for one of the avoidable reasons below, not because the work genuinely needs
outside files.
Diagnose
Don't guess about past friction — measure it. The plugin ships an analyzer,
scripts/friction-report.py, that re-reads the hook decisions Claude Code
already recorded in the local session transcripts and ranks them by category,
offending path, and triggering command. Run it first so the diagnosis is
grounded in the user's real prompt history:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/friction-report.py" --repo "$(basename "$CLAUDE_PROJECT_DIR")"
This reports the friction ratio (ask+deny share), a By category breakdown, the top offending paths, and the top triggering commands for the current project over the last 7 days. The ratio's denominator counts only decisions the hook emitted — a silent defer on an unguarded command leaves no record — so it is a share of the hook's own decisions, not of every Bash call. Useful adjustments:
--since 24h/--since 2026-06-01/--since all— widen or narrow the window (default7d).--repo ''— drop the project filter to see friction across every repo.--raw— show exact path tokens instead of collapsing per-session temp paths.--json— machine-readable, if you'd rather parse it than read the table.
Fall back gracefully. If the script can't be found ($CLAUDE_PLUGIN_ROOT
unset — try the in-repo path scripts/friction-report.py), exits with "No
transcripts …", or prints "No guard decisions found" (a fresh setup with no
recorded prompts yet), skip the data step and diagnose from the most recent
prompts in this session instead — the hook's reason text names the offending
path and the fix for each.
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 Changed ece1d40be3d4
- 12d ago First seen · 132 lines · 69 tokens per session scan A 39269ce11770
reduce-workspace-guard-prompts is a skill published in the GitHub repository karlkfi/claude-bouncer (3 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,670 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
debugging-strategies
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
sql-optimization-patterns
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
parallel-debugging
Debug complex issues using competing hypotheses with parallel investigation, evidence collection, and root cause arbitration. Use this skill when debugging bugs with multiple potential causes, performing root cause analysis, or organizing parallel investigation workflows.
error-handling-patterns
Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.
spark-optimization
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.