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/java-engineernpx skills add nelson820125/iforgeai --skill java-engineergit clone --depth 1 https://github.com/nelson820125/iforgeaiWhat 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 | $0.00071 | $0.02499 |
| Opus 5 | $0.00036 | $0.01249 |
| Sonnet 5 | $0.00014 | $0.00500 |
| Haiku 4.5 | $0.00007 | $0.00250 |
Grade A, and why
java-engineer 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 2d 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 — 193 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 and code comments in that language. If the file is absent or the field is unset, default to en-US.
DB Approach Rule
Read db_approach from .ai/context/workflow-config.md before starting any database-related implementation:
database-first(default when unset): The authoritative schema is defined in.ai/temp/db-init.sqlproduced by the DBA. You must implement MyBatis Plus entity classes and Mapper code that matches this schema exactly. Do NOT use schema-generation tools (e.g.spring.jpa.hibernate.ddl-auto=create) to initialise the database — the database is initialised from the DBA's SQL script.code-first: You are responsible for driving the schema via migration tools (Flyway or Liquibase). Workflow:- Read
.ai/temp/db-design.md(DBA design document) as the reference for field types, constraints, indexes, and default values - Implement entity classes faithfully according to the design document
- Create a Flyway migration script
V{n}__{description}.sqlor Liquibase changeset - Document each migration task in the WBS and work log with its version and purpose
- Read
Phase Mode
This skill operates in two modes depending on how it is invoked:
| Mode | Trigger | Task | Output |
|---|---|---|---|
/contract |
digital-team Phase 5a |
Define full API contract schemas in api-contract.md |
.ai/temp/api-contract.md (fully detailed, ready for frontend review) |
/develop (default) |
digital-team Phase 6b, or standalone invocation |
Implement backend code based on api-contract.md + wbs.md |
Source code + work log |
Contract mode (/contract) rules:
- Read
.ai/temp/api-contract.md(architect's skeleton) and.ai/temp/wbs.md - Fill in Request schema, Response schema, HTTP status codes, and validation rules for each endpoint
- Do NOT write implementation code in this mode — output is documentation only
- The completed contract is reviewed by the frontend engineer before development begins
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.
- 2d ago First seen · 193 lines · 0 tokens per session scan A 00154f921d56
java-engineer is a skill published in the GitHub repository nelson820125/iforgeai (8 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 2,499 once invoked, about $0.0004 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.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.