forge-validate

A validation helper for checking one module from the current Forge development plan. It runs that module’s listed verification commands and reports the results and retry history.

In plain words
What is it for?
Use it to validate modules such as m1 or m2, review passed and failed checks, and decide whether to retry or escalate.
Why use it?
It gathers the relevant checks and past attempts in one place, making it easier to see whether a module is ready or needs debugging.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/tt-wang/forge/forge-validate
Any agent
npx skills add TT-Wang/forge --skill forge-validate
Clone the repo
git clone --depth 1 https://github.com/TT-Wang/forge

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 249 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00249
Opus 5 $0.00008 $0.00125
Sonnet 5 $0.00003 $0.00050
Haiku 4.5 $0.00002 $0.00025

Measured yesterday against content hash e4f515c600a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge-validate 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.

skills/forge-validate/SKILL.md · 31 lines

What it actually says

Validate a specific module from the active forge plan. Prefix all output with [forge:validate].

  1. Read the latest plan from .forge/plans/ (most recent JSON file)
  2. Find the module matching the argument (e.g., "m1", "m2")
  3. Call mcp__forge__validate with that module's verify commands and files
  4. Call mcp__forge__iteration_state to get retry history
  5. Report results:
## Validation: {module title}

**Status:** PASSED / FAILED
**Score:** {X}/{Y} checks passed
**Stagnant:** yes/no
**Attempt:** {N}

### Results
- [PASS] npm test -- --grep 'auth'
- [FAIL] npx tsc --noEmit (error: TS2345 in src/auth.ts:42)

### Recommendation
{PASS / RETRY_WITH_DEBUGGER / ESCALATE}
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.

  1. yesterday First seen · 31 lines · 15 tokens per session scan A e4f515c600a3

Subscribe to this mod's changes

forge-validate is a skill published in the GitHub repository TT-Wang/forge (35 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 249 once invoked, about $0.0001 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.