agentmods.dev

capshelf-perf-harness

capshelf-perf-harness is a skill for Claude Code from genged/capshelf. It costs 54 tokens per session (557 once invoked), scanned A, original, MIT.

A performance and correctness test harness for the capshelf program. It measures response time and Git process use, and checks that two builds produce the same results.

In plain words
What is it for?
Use it to benchmark builds, compare a branch with a release, trace Git calls, and test both normal and split data layouts.
Why use it?
It helps find unnecessary repeated Git work and catch behavior differences when changing or comparing builds.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

not rated 22repo yesterday A scan 54 tokens original MIT

Good fit Use it to benchmark builds, compare a branch with a release, trace Git calls, and test both normal and split data layouts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/genged/capshelf/capshelf-perf-harness
View source ↗ genged/capshelf
Install

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.

Any agent
npx skills add genged/capshelf --skill capshelf-perf-harness
Clone the repo
git clone --depth 1 https://github.com/genged/capshelf

Made for: Claude Code.

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.

agentmods badge for capshelf-perf-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/genged/capshelf/capshelf-perf-harness/github.svg)](https://agentmods.dev/skills/genged/capshelf/capshelf-perf-harness)
Your own site
<a href="https://agentmods.dev/skills/genged/capshelf/capshelf-perf-harness"><img src="https://agentmods.dev/badge/skills/genged/capshelf/capshelf-perf-harness/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.

agentmods 80×15 button for capshelf-perf-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/genged/capshelf/capshelf-perf-harness"><img src="https://agentmods.dev/badge/skills/genged/capshelf/capshelf-perf-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 557 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00557
Opus 5.5 $0.00022 $0.00223
Sonnet 5.5 $0.00011 $0.00111
Haiku 4.5 $0.00005 $0.00056

Measured yesterday against content hash 3eefdd87f329, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

capshelf-perf-harness 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 yesterday.

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.

.claude/skills/capshelf-perf-harness/SKILL.md · 54 lines

What it actually says

capshelf-perf-harness

The tools are in tools/perf/. docs/performance.md explains each one and how to read the numbers. Read it before you report a result.

Compare two builds

  1. Build each binary and copy it out of dist/. The next build overwrites dist/capshelf. 
    bun run build && cp dist/capshelf /tmp/capshelf-new
    For an older ref, extract it with git archive <ref> | tar -x -C <dir>, link this tree's node_modules into <dir>, and run bun run build there. Do not check out another ref in this working tree.
  2. Prove equal results on both fixture shapes. Each command must print equal: and exit 0: 
    tools/perf/equiv.sh /tmp/capshelf-old /tmp/capshelf-new
SPLIT=1 tools/perf/equiv.sh /tmp/capshelf-old /tmp/capshelf-new
  3. Measure both shapes: 
    tools/perf/bench.sh /tmp/capshelf-old /tmp/capshelf-new
SPLIT=1 tools/perf/bench.sh /tmp/capshelf-old /tmp/capshelf-new
    Add EXTRA=20000 once to show that no cost follows the size of the data repo.

Find what to batch

SPLIT=1 tools/perf/trace.sh /tmp/capshelf-new status

A line whose count is near the item count is a Git call that runs once per item.

Rules

  • Report the Git process count first and the wall time second. The count is exact. Wall time changes by 10 to 20 percent between runs.
  • equiv.sh passing is necessary, not sufficient. A new batched read also needs a unit test that compares it with the read it replaces, on random inputs. Then break the batching on purpose and confirm that the test fails.
  • The test suites remove their temporary files after a passing run. If df -i / still shows few free inodes, ask the user before you delete files that you did not create.
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.

  1. yesterday First seen · 54 lines · 54 tokens per session scan A 3eefdd87f329

Subscribe to this mod's changes

capshelf-perf-harness is a skill published in the GitHub repository genged/capshelf (22 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 557 once invoked, about $0.0002 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 2026-11-06.

Analytics and metricsTestingagent-skillsaicodexskillsteam-standards
Related

capshelf-perf-harness compared with skills from other repositories

capshelf-perf-harness next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
capshelf-perf-harnessgenged/capshelfSkill22yesterdayMITA54Claude Code
claude-md-improveranthropics/claude-plugins-officialSkill46kyesterdayApache-2.0A82Claude Code
agent-platform-model-registrygoogle/skillsSkill22kyesterdayApache-2.0A60Claude Code, Codex
gke-reliabilitygoogle/skillsSkill22kyesterdayApache-2.0A85Claude Code, Codex
gke-workload-securitygoogle/skillsSkill22kyesterdayApache-2.0A171Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skillsSkill22kyesterdayApache-2.0A132Claude Code, Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code