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/ktoulgaridis/forge/doctorgit clone --depth 1 https://github.com/ktoulgaridis/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/ktoulgaridis/forge/doctor)<a href="https://agentmods.dev/commands/ktoulgaridis/forge/doctor"><img src="https://agentmods.dev/badge/commands/ktoulgaridis/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 | $0.00018 | $0.00660 |
| Opus 5 | $0.00009 | $0.00330 |
| Sonnet 5 | $0.00004 | $0.00132 |
| Haiku 4.5 | $0.00002 | $0.00066 |
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.
└─ Add to ~/.claude/settings.json: How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:doctor — Check the forge environment
Run inside a forge-stamped project. Reports what's working, what's missing, and what to install.
Invocation
/forge:doctor
What this command does
- Read
.forge.config.yaml - For every adapter listed in
tracker,scm,integrations:- Read the adapter's
required_clisandoptional_mcp_servers - Test each CLI:
command -v <cli>; if present, run a smoke check (gh auth status,glab auth status,jira me, etc.) - Test each MCP server: check Claude Code's
/mcpregistration
- Read the adapter's
- For every role in
roles[]:- Verify
roles/<name>.mdexists in the project - Verify
.claude/skills/prime/SKILL.mdrecognizes the role name
- Verify
- For the wiki structure:
- Verify
CLAUDE.mdexists at root - Verify
decisions/,services/,themes/,roles/dirs exist - Verify
requirements/(or equivalent canonical-requirements dir) exists
- Verify
- Print a tabular report:
forge:doctor v0.1.0 ────────────────────────────────── ✓ N passed ⚠ M warnings ✖ K errors
CLIs (X/Y passed)
✓ git
✓ gh — authed as <user>
⚠ jira — installed but not configured (run `jira init`)
✖ glab — not installed
└─ Install: brew install glab (or apt install glab)
MCP servers (X/Y registered)
✓ figma — connected
⚠ slack — declared in config but not registered in /mcp
└─ Add to ~/.claude/settings.json:
{ "mcpServers": { "slack": { "type": "http", "url": "..." } } }
Roles (X/Y present)
✓ orchestrator, architect, implementer, reviewer, wiki-maintainer, migration-analyst
Wiki structure (passed)
✓ CLAUDE.md present
✓ decisions/, services/, themes/, roles/ all populated
- Exit code 0 if all checks pass; non-zero if errors
When to run
- After
/forge:new— confirms the bootstrap landed cleanly - After
/forge:add-adapter— confirms the new integration's dependencies are met - Periodically — catches local environment drift (a CLI auth expired, etc.)
- In CI for the wiki repo — verify the wiki is forge-compliant
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 · 69 lines · 18 tokens per session scan B b94bebc709c2
doctor is a command published in the GitHub repository ktoulgaridis/forge (10 stars, last pushed 8d ago), licensed MIT. It adds 18 tokens to every session and 660 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.