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/ariegoldkin/claude-forge/doctorgit clone --depth 1 https://github.com/ArieGoldkin/claude-forgeWrote 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/ariegoldkin/claude-forge/doctor)<a href="https://agentmods.dev/commands/ariegoldkin/claude-forge/doctor"><img src="https://agentmods.dev/badge/commands/ariegoldkin/claude-forge/doctor.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 | $0.00017 | $0.04757 |
| Opus 5 | $0.00009 | $0.02379 |
| Sonnet 5 | $0.00003 | $0.00951 |
| Haiku 4.5 | $0.00002 | $0.00476 |
Grade B, and why
doctor scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
CACHE_DIR=$(find ~/.claude/plugins/cache -type d -name "$PLUGIN" | head -1) How it starts
The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/doctor - Plugin System Diagnostics
Comprehensive health check across all installed claude-forge. Shows what's installed, what's working, and what needs attention.
Complements: /check-maintenance (continuity files) and /continuity-metrics (session state). This command covers the plugin system itself.
Execution Steps
Step 1: Detect Installed Plugins
On CC v2.1.163+ the native listing is the fastest inventory — but treat it as a claim, not a
verdict. It renders from installed_plugins.json, so it prints ✔ enabled even when the
plugin's files have been deleted. Always pair it with Step 1a.
claude plugin list --enabled || echo "native list unavailable (CC < 2.1.163)"
Fall back to scanning known plugin directories on older CC:
# Check marketplace cache for each plugin
PLUGINS=("ctk" "etk" "dtk" "atk" "ftk")
for PLUGIN in "${PLUGINS[@]}"; do
# Check marketplace cache
CACHE_DIR=$(find ~/.claude/plugins/cache -type d -name "$PLUGIN" | head -1)
if [ -n "$CACHE_DIR" ]; then
VERSION=$(grep -h '"version"' "$CACHE_DIR"/*/.claude-plugin/plugin.json | head -1)
echo "INSTALLED: $PLUGIN ($VERSION)"
else
echo "NOT INSTALLED: $PLUGIN"
fi
done
This glob matches every version folder ever installed, including stale ones left behind by earlier upgrades — which is why Step 1a is mandatory before trusting the result.
Also check for local dev plugins via --plugin-dir:
# Check if running from monorepo (local dev) — source dirs use the legacy long names
if [ -f "plugins/continuity-toolkit/.claude-plugin/plugin.json" ]; then
echo "LOCAL DEV MODE: Running from monorepo"
fi
Step 1a: Verify Recorded Install Paths Resolve
The Step 1 glob matches any version folder, including stale ones; installed_plugins.json records
one specific installPath per plugin. A DANGLING row means the two disagree.
Why this check exists, how to interpret a
DANGLINGrow, and how to repair it live in thedoctorskill's Step 1a (skills/doctor/SKILL.md) — the single source of truth. Read it before interpreting aDANGLINGrow; do not restate its reasoning here.
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.
- 5d ago First seen · 397 lines · 17 tokens per session scan B 0db8b845a427
doctor is a command published in the GitHub repository ArieGoldkin/claude-forge (6 stars, last pushed 28d ago), licensed MIT. It adds 17 tokens to every session and 4,757 once invoked, about $0.0001 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 2026-08-31.
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.