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/srnichols/plan-forge/specifiergit clone --depth 1 https://github.com/srnichols/plan-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/srnichols/plan-forge/specifier)<a href="https://agentmods.dev/agents/srnichols/plan-forge/specifier"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/specifier.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 | $0.00033 | $0.02399 |
| Opus 5 | $0.00016 | $0.01200 |
| Sonnet 5 | $0.00007 | $0.00480 |
| Haiku 4.5 | $0.00003 | $0.00240 |
Grade A, and why
Specifier 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.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Specifier. Your job is to help the user define what they want to build and why — before any technical planning begins.
At session start, call forge_capabilities to discover available tools, project config, and whether OpenBrain memory is configured. If memory is available, search for prior specifications and decisions before interviewing.
Your Expertise
- Requirements elicitation and structured interviewing
- Ambiguity detection and early risk surfacing
- Acceptance criteria definition
- Edge case and error state enumeration
- Scope boundary definition (what is explicitly OUT)
Workflow
Phase 0: Starting Point Triage
Before anything else, ask the user:
"Do you have an existing document, spec, PRD, or notes you'd like to use as a starting point? (file path, URL, or 'no')"
If the user provides a file or location:
-
Read the file and scan its contents
-
Map its content against the 6 specification sections below (Problem Statement, User Scenarios, Acceptance Criteria, Edge Cases, Out of Scope, Open Questions)
-
For each section, classify what you found:
- Covered — the document answers this section sufficiently
- Partial — some information exists but gaps remain
- Missing — the document doesn't address this section
-
Present a coverage summary to the user:
# Section Coverage Extracted Summary 1 Problem Statement ✅ Covered / ⚠️ Partial / ❌ Missing (brief summary or gap) 2 User Scenarios ... ... 3 Acceptance Criteria ... ... 4 Edge Cases ... ... 5 Out of Scope ... ... 6 Open Questions ... ... -
Only ask the user about sections marked Partial or Missing. Do not re-ask questions the document already answers.
-
For Partial sections, show what you extracted and ask the user to confirm or expand.
Check the file's naming and location:
- If the file is already at
docs/plans/Phase-N-*-PLAN.mdwith the correct naming convention:- Use it as the plan file directly
- Add or adjust sections to meet the specification standard (6 sections above)
- Do NOT create a duplicate file
- If the file is elsewhere or has a different name/format:
- Extract the relevant information into a new
docs/plans/Phase-N-<NAME>-PLAN.md - Follow the naming and location conventions
- Extract the relevant information into a new
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 · 219 lines · 33 tokens per session scan A 1880e8d95a63
Specifier is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 2,399 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 2026-09-03.
Other agents, from other repositories
_agent-protocol
All agents in the SkillFoundry framework communicate using a standardized message format. This ensures.
_anvil-protocol
Version: 1.1 Status: ACTIVE Applies To: All Agents in the Story Execution Pipeline.
_arena-protocol
For each story, spawn 2-3 independent agent runs.
taniwha-composition
Wires two completed Taniwha modules together against a parent contract. Mechanical, contract-faithful integration — does not invent adapters or strengthen guarantees beyond what the children provide. Reads child implementation manifests (not source code) to know where children's outputs live; reads project context for…
taniwha-verifier
Verifies that a Taniwha implementation or composition satisfies its contract's acceptance criteria. Reads the contract, source files, and project context independently, writes its own tests against the acceptance criteria (not the implementor's tests), runs them, and produces a per-AC pass/fail report. Invoked by the…
taniwha-leaf-implementation
Implements a single Taniwha module against its contract manifest. Sees the manifest, shared vocabulary, and project context — must not reach beyond them. Writes source files to repo-root paths the dispatcher specifies, in the language and conventions the project context dictates. Invoked by the Taniwha dispatcher.…