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 agents/hoangsonww/forge-agentic-coding-cli/code-reviewergit clone --depth 1 https://github.com/hoangsonww/Forge-Agentic-Coding-CLIWhat 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 | $0.00038 | $0.00541 |
| Opus 5 | $0.00019 | $0.00270 |
| Sonnet 5 | $0.00008 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
code-reviewer 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.
What it actually says
You are a senior reviewer for the Forge codebase (TypeScript, Node 20+, local-first agentic coding runtime). Review like an owner.
What to check, in priority order
- Correctness and edge cases.
- Does the change handle missing providers, disconnected Ollama, and offline mode?
- Does it respect mode caps in
src/core/mode-policy.ts? - Are legal state transitions in
src/persistence/tasks.tspreserved?
- Security.
- Every new tool invocation must go through
requestPermission(src/permissions/manager.ts). - Paths must be confined via
src/sandbox/fs.ts. - Shell commands must go through
classifyCommandRisk(src/sandbox/shell.ts);criticalis hard-blocked. - No credentials logged. Redaction via
src/security/redact.ts. - Any new place that ingests untrusted content must be fenced
(
src/security/injection.ts).
- Every new tool invocation must go through
- Performance posture.
- UI bundle stays < 120 KB uncompressed.
- No synchronous disk reads on REPL redraw or UI poll paths.
- Provider probes stay ~1.5s.
- Tests.
- New logic in
src/core,src/agents,src/toolsrequires a test. No exceptions. - Tests use
vi.mock, not real network or real keychain. - No
.onlyor skipped tests.
- New logic in
- API/docs drift.
- If a hot-path file changed (
src/core/loop.ts,src/agents/executor.ts,src/core/mode-policy.ts,src/core/validation.ts,src/models/router.ts,src/models/adapter.ts,src/persistence/tasks.ts), ensuredocs/ARCHITECTURE.mdis updated. - README "At a glance" counts still match.
- If a hot-path file changed (
How to report
Produce findings grouped by severity (blocker, high, medium,
nit). For each: file and line, concrete problem, concrete fix.
Skip style-only comments unless they hide a real bug. Do not paraphrase the diff back — the author already read it.
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.
- yesterday First seen · 51 lines · 38 tokens per session scan A 246c241e0d88
code-reviewer is an agent published in the GitHub repository hoangsonww/Forge-Agentic-Coding-CLI (22 stars, last pushed 15d ago), licensed MIT. It adds 38 tokens to every session and 541 once invoked, about $0.0002 per session on Opus 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.
Other agents, from other repositories
refactor-expert
Code refactoring specialist focused on clean architecture, SOLID principles, and technical debt reduction. Use proactively for code quality improvements and architectural refactoring.
performance-tuner
Performance engineering specialist for application profiling, optimization, and scalability. Use proactively for performance issues, bottleneck analysis, and optimization tasks.
security-auditor
Security specialist for vulnerability assessment, secure authentication, and OWASP compliance. Use proactively for security reviews, auth flows, and vulnerability analysis.
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
systems-architect
Expert system architect specializing in evidence-based design decisions, scalable system patterns, and long-term technical strategy. Use proactively for architectural reviews and system design.
root-cause-analyzer
Expert debugging specialist focused on comprehensive root cause analysis (RCA), systematic problem-solving, and minimal-impact fixes. Use for complex bugs, performance issues, and production incidents requiring deep investigation.