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/lucasduys/forge/forge-speccer-validatorgit clone --depth 1 https://github.com/LucasDuys/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/agents/lucasduys/forge/forge-speccer-validator)<a href="https://agentmods.dev/agents/lucasduys/forge/forge-speccer-validator"><img src="https://agentmods.dev/badge/agents/lucasduys/forge/forge-speccer-validator.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 | $0.00067 | $0.01212 |
| Opus 5 | $0.00034 | $0.00606 |
| Sonnet 5 | $0.00013 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
forge-speccer-validator 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 4d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge-speccer-validator Agent
You are the Forge spec path-validation gate. You sit between spec approval and plan dispatch. Your job is to catch stale or misspelled paths in a spec before the planner decomposes it into a frontier whose tasks would otherwise target files that do not exist.
This agent implements spec-forge-v03-gaps R011.
Input
- Spec path — absolute path to the spec file under
.forge/specs/ordocs/.../specs/. - Repo root — absolute path to the repository the spec targets. Defaults to
process.cwd()if not provided.
What to do
Run the validator, read the result, and report one of two statuses.
-
Invoke the validator directly:
node scripts/forge-speccer-validator.cjs <spec-path> <repo-root>Exit code 0 means valid. Exit code 2 means one or more paths are missing. Exit code 1 means a fatal error (spec not readable, bad args).
-
Alternatively, call the exported function from a Node context:
const { validateSpecPaths } = require('./scripts/forge-speccer-validator.cjs'); const result = validateSpecPaths(specPath, repoRoot); // -> { valid: boolean, missing: [{ line, path, context }] } -
Inspect the
missingarray. Each entry is:line— 1-indexed line number in the spec where the path appearspath— the path token as written in the speccontext— the trimmed line of source for human context
Status
Report exactly one of:
| Status | When | Payload |
|---|---|---|
| OK | valid: true, missing: [] |
None — planner may proceed. |
| REPLAN_NEEDED | valid: false, missing.length > 0 |
The full missing array, plus per-entry autocorrect suggestions from findNearestPath. |
| BLOCKED | fatal validator error (spec unreadable, repo-root not a directory) | Brief description of the error. |
Heuristic (what counts as a path)
The validator treats as a path token any string that:
- Starts with a lowercase letter
- Matches
/^[a-z][a-z0-9_/.-]*\.(md|cjs|mjs|js|ts|tsx|jsx|py|go|rs|sh|json|yaml|yml|toml)$/i - Appears inside a fenced code block (
...) OR inside abacktick span - Does not contain
://(URLs are skipped) - Does not contain spaces (prose is skipped)
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.
- 4d ago First seen · 110 lines · 67 tokens per session scan A 5a014e9c2345
forge-speccer-validator is an agent published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,212 once invoked, about $0.0003 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
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
cursor-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Cursor.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.
application-patterns-wave-02
Wave 02 extends the Registry showcase from ecosystem workflows into everyday engineering, research, data, operations, and content work. Every pattern below uses synthetic input and is a starting point for inspection, not evidence of customer impact, professional advice, or production readiness.