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 commands/kumaran-is/claude-code-onboarding/autoresearchgit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/commands/kumaran-is/claude-code-onboarding/autoresearch)<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/autoresearch"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/autoresearch.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 5.1 | $0.00044 | $0.02197 |
| Opus 5 | $0.00022 | $0.01099 |
| Sonnet 5 | $0.00009 | $0.00439 |
| Haiku 4.5 | $0.00004 | $0.00220 |
Grade B, and why
autoresearch scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > "$CLAUDE_PROJECT_DIR/.claude/autoresearch.local.md" <<EOF How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoresearch — Autonomous Improvement Loop
Measure → Improve → Verify → Keep or Rollback → Repeat.
Unlike /ralph-loop (which runs blind), this loop is metric-gated: changes are committed only when the score improves. Regressions are automatically rolled back with git reset --hard.
Step 1 — Parse arguments and set defaults
METRIC="${METRIC:-all}"
TARGET_REDUCTION="${TARGET_REDUCTION:-5}"
MAX_ITERATIONS="${MAX_ITERATIONS:-10}"
ITERATION=1
# Parse $ARGUMENTS
while [[ $# -gt 0 ]]; do
case "$1" in
--metric) METRIC="$2"; shift 2 ;;
--target) TARGET_REDUCTION="$2"; shift 2 ;;
--max-iterations) MAX_ITERATIONS="$2"; shift 2 ;;
*) shift ;;
esac
done
echo ""
echo "🔬 Autoresearch loop starting"
echo " Metric: $METRIC"
echo " Target/iter: -$TARGET_REDUCTION issues per loop"
echo " Max iterations: $MAX_ITERATIONS"
echo " Stop: /cancel-ralph (shares the same cancel mechanism)"
echo ""
Step 2 — Measure baseline
Run the baseline metric measurement now. Choose based on $METRIC:
If $METRIC is flutter or all:
FLUTTER_WARNINGS=$(flutter analyze 2>&1 | grep -c "warning\|error\|hint" || echo 0)
FLUTTER_TODOS=$(grep -r "TODO\|FIXME\|HACK" lib/ --include="*.dart" 2>/dev/null | wc -l | tr -d ' ' || echo 0)
echo "Flutter warnings: $FLUTTER_WARNINGS"
echo "Flutter TODOs: $FLUTTER_TODOS"
If $METRIC is nestjs or all:
NESTJS_ANY=$(grep -r ": any\b\|as any\b" src/ --include="*.ts" 2>/dev/null | grep -v ".spec.ts" | wc -l | tr -d ' ' || echo 0)
NESTJS_CONSOLE=$(grep -r "console\.log\|console\.warn\|console\.error" src/ --include="*.ts" 2>/dev/null | grep -v ".spec.ts" | wc -l | tr -d ' ' || echo 0)
NESTJS_TODOS=$(grep -r "TODO\|FIXME" src/ --include="*.ts" 2>/dev/null | wc -l | tr -d ' ' || echo 0)
echo "NestJS 'any' types: $NESTJS_ANY"
echo "NestJS console.log: $NESTJS_CONSOLE"
echo "NestJS TODOs: $NESTJS_TODOS"
If $METRIC is angular or all:
ANGULAR_ANY=$(grep -r ": any\b\|as any\b" projects/ --include="*.ts" 2>/dev/null | grep -v ".spec.ts" | wc -l | tr -d ' ' || echo 0)
ANGULAR_CONSOLE=$(grep -r "console\.log\|console\.warn\|console\.error" projects/ --include="*.ts" 2>/dev/null | grep -v ".spec.ts" | wc -l | tr -d ' ' || echo 0)
echo "Angular 'any' types: $ANGULAR_ANY"
echo "Angular console.log: $ANGULAR_CONSOLE"
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.
- 2d ago First seen · 181 lines · 44 tokens per session scan B 3668a955ea3b
autoresearch is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 2,197 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.