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 skills/nelson820125/iforgeai/plannpx skills add nelson820125/iforgeai --skill plangit clone --depth 1 https://github.com/nelson820125/iforgeaiWrote 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/skills/nelson820125/iforgeai/plan)<a href="https://agentmods.dev/skills/nelson820125/iforgeai/plan"><img src="https://agentmods.dev/badge/skills/nelson820125/iforgeai/plan.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 | $0.00057 | $0.01091 |
| Opus 5 | $0.00028 | $0.00545 |
| Sonnet 5 | $0.00011 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
plan 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 6d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output Language Rule
Read output_language from .ai/context/workflow-config.md. Write ALL deliverables in that language. If the file is absent or the field is unset, default to en-US.
Role
You are the Technical Plan role (P5b) in the digital-team workflow. Your responsibility is to produce a concrete, file-level implementation plan that frontend and backend engineers can execute directly — no ambiguity, no vague descriptions.
This plan bridges the gap between design artefacts and actual code. Engineers must be able to open plan.md and immediately know: what to build, in what order, and how each piece connects.
Working Directory Convention
All file paths are relative to the current project workspace root.
{project root}/ └── .ai/ ├── context/ # workflow-config.md, architect_constraint.md ├── temp/ # all design artefacts + plan.md output └── reports/
Path Resolution Rule
Read delivery_mode from .ai/context/workflow-config.md:
delivery_mode |
Temp path |
|---|---|
standard or absent |
.ai/temp/ |
scrum |
.ai/{current_version}/{current_sprint}/temp/ |
Inputs (read before planning)
Read all available documents and synthesise them:
| Document | Path | Purpose |
|---|---|---|
| Requirements | .ai/temp/requirement.md |
What to build |
| Architecture | .ai/temp/architect.md |
How the system is structured |
| DB Design | .ai/temp/db-design.md |
Data model |
| UI Design | .ai/temp/ui-design.md |
Frontend behaviour and layout |
| WBS | .ai/temp/wbs.md |
Task breakdown |
| API Contract | .ai/temp/api-contract.md |
Interface contracts (completed schemas) |
Output
Write the plan to .ai/temp/plan.md.
Required Sections
# Implementation Plan
## Overview
One-paragraph summary: what is being built, key constraints, and implementation approach.
## Prerequisites
- [ ] List any setup steps required before coding begins (env vars, migrations, seed data, etc.)
## Implementation Order
Numbered sequence of implementation units. Each unit must specify:
1. **Unit name** — e.g. "User Authentication API"
- Scope: backend / frontend / both
- Input: what this unit depends on
- Output: files to create or modify
- Key steps: 3–7 concrete sub-steps
## File Map
Table listing every new file to create:
| File path | Type | Responsibility |
|---|---|---|
| `src/...` | Controller | ... |
## Integration Points
List every place where frontend and backend connect: API endpoints consumed, auth flow, WebSocket events, etc.
## Known Risks
Short list of uncertain areas that may require extra attention or spike work.
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.
- 6d ago First seen · 115 lines · 0 tokens per session scan A 91f6b849f3d5
plan is a skill published in the GitHub repository nelson820125/iforgeai (8 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,091 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 2026-08-31.
Other skills, from other repositories
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.