What is collect-cli-fixtures?

A workflow for capturing real Claude or Gemini command-line streaming output as JSON Lines files. JSON Lines means one JSON object per line, which is useful for recording event streams.

Creating print or interactive CLI captures, exporting records from the database, validating every fixture line, checking event-type counts, replacing session identifiers, and scanning for API keys.

It gives parser tests real protocol data and helps detect malformed records, missing event types, changed CLI output, or leaked secrets.

How recca0120/code-quest configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to recca0120/code-quest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/recca0120/code-quest/main/.claude/skills/collect-cli-fixtures/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/recca0120/code-quest

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/recca0120/code-quest/collect-cli-fixtures/github.svg)](https://agentmods.dev/skills/recca0120/code-quest/collect-cli-fixtures)

Your own site

<a href="https://agentmods.dev/skills/recca0120/code-quest/collect-cli-fixtures"><img src="https://agentmods.dev/badge/skills/recca0120/code-quest/collect-cli-fixtures/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/skills/recca0120/code-quest/collect-cli-fixtures"><img src="https://agentmods.dev/badge/skills/recca0120/code-quest/collect-cli-fixtures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 579 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	$0.00044	$0.00579
Opus 5.5	$0.00018	$0.00232
Sonnet 5.5	$0.00009	$0.00116
Haiku 4.5	$0.00004	$0.00058

Measured 2mo ago against content hash 3a8ba3c6b889, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

collect-cli-fixtures 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.

.claude/skills/collect-cli-fixtures/SKILL.md · 75 lines

What it actually says

Collect CLI Fixtures

Capture Script

scripts/capture-fixture.sh <name> [prompt]

Print mode

claude --output-format stream-json -p "say hello" 2>/dev/null > /tmp/claude-simple-text.jsonl

Interactive mode (control protocol)

mkfifo /tmp/claude-stdin
claude --output-format stream-json --input-format stream-json --verbose \
  < /tmp/claude-stdin 2>/dev/null | tee /tmp/claude-interactive.jsonl &
exec 3>/tmp/claude-stdin
# Send control_request JSON via fd 3, sleep between requests
exec 3>&-; kill %1 2>/dev/null; rm /tmp/claude-stdin

From DB

mysql -u root -h 127.0.0.1 -P 3306 code_quest -N -e \
  "SELECT raw FROM raw_entries WHERE raw LIKE '{\"type\":\"<type>\"%' LIMIT 1;"

Validation

# Every line must be valid JSON
while IFS= read -r line; do
  echo "$line" | jq . > /dev/null 2>&1 || echo "INVALID: $line"
done < /tmp/fixture.jsonl

# Check event type distribution
cat /tmp/fixture.jsonl | jq -r '.type' | sort | uniq -c

Sanitization

sed -i '' 's/"session_id":"[^"]*"/"session_id":"test-session-id"/g' fixture.jsonl
grep -l "sk-" fixture.jsonl  # Check for API key leaks

Destination

apps/summoner/src/__fixtures__/claude/
├── real/<name>.jsonl        # From DB or real CLI
└── synthetic/<name>.jsonl   # Hand-crafted (mark for future replacement)

Checklist

CLI installed and working
Fixture captured from real CLI (never hand-written)
Every line is valid JSON
Sensitive data sanitized
Placed in correct directory (real/ or synthetic/)
Tracking doc updated (docs/fixture-capture-tracking.md)

Reference

Tracking: docs/fixture-capture-tracking.md
Fixture-Driven TDD: /fixture-driven-tdd

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 · 75 lines · 44 tokens per session scan A 3a8ba3c6b889

Subscribe to this mod's changes

collect-cli-fixtures is a skill published in the GitHub repository recca0120/code-quest (11 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 579 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 2026-08-30.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

code-quest: Skill for Claude Code