Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rjmurillo/ai-agents/plugin install project-toolkitWrote 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/rjmurillo/ai-agents/skillforge)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/skillforge"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/skillforge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/skillforge"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/skillforge.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00152 | $0.03777 |
| Opus 5.5 | $0.00061 | $0.01511 |
| Sonnet 5.5 | $0.00030 | $0.00755 |
| Haiku 4.5 | $0.00015 | $0.00378 |
Grade A, and why
skillforge 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 3d 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SkillForge 4.1 - Intelligent Skill Router and Creator
Analyzes any input to find, improve, compose, or create the right skill.
Boundary with skillify: SkillForge starts from a goal or request. To turn a
workflow you just completed into a skill, driven by the session's tool calls,
branches, and errors, use skillify.
Quick Start
SkillForge accepts direct creation requests, skill improvement requests, skill lookup questions, task prompts, error messages, URLs, and code snippets. It routes first, then creates only when no existing skill covers the need.
SkillForge: create a skill for automated code review
-> Creates a new skill after checking for duplicates
help me debug this TypeError
-> Recommends an existing debugging skill
improve the testgen skill to handle React components better
-> Loads the skill and enters improvement mode
do I have a skill for database migrations?
-> Recommends matching database skills
See references/overview-and-triggers.md for the full examples, triggers, routing diagram, and command summary. See references/phase0-triage.md for the full triage flow and script examples.
Triggers
Creation Triggers
SkillForge: {goal}: full autonomous skill creationcreate skill: natural language activationdesign skill for {purpose}: purpose-first creationultimate skill: maximum quality creation pathSkillForge --plan-only: generate specification without execution
Routing Triggers
{any input}: analyze and route automaticallydo I have a skill for: search existing skillswhich skillorwhat skill: recommend matching skillsimprove {skill-name} skill: improve an existing skillhelp me withorI need to: detect task and route
| Input | Output | Quality Gate |
|---|---|---|
| Any input | Triage -> Route -> Action | Phase 0 analysis |
| Explicit create | New skill | Unanimous panel approval |
| Skill question | Skill recommendation | Match confidence >=60% |
What ships with it
39 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 533 B
- .skillignore 209 B
- assets/templates/script-template.py 8.3 KB runs code
- assets/templates/skill-md-template.md 1.4 KB
- assets/templates/skill-spec-template.xml 17 KB
- references/architecture-patterns.md 1.0 KB
- references/changelog.md 2.0 KB
- references/configuration.md 530 B
- references/degrees-of-freedom.md 4.3 KB
- references/evolution-scoring.md 8.5 KB
- references/evolution-timelessness.md 1.1 KB
- references/external-skill-source-adaptation.md 3.7 KB
- references/iteration-guide.md 3.4 KB
- references/modularity-guidelines.md 3.9 KB
- references/multi-lens-framework.md 10 KB
- references/output-structure.md 5.6 KB
- references/overview-and-triggers.md 5.6 KB
- references/phase0-triage.md 6.1 KB
- references/phase1-analysis-deep-dive.md 5.7 KB
- references/phase2-specification-deep-dive.md 2.0 KB
- references/phase3-generation-deep-dive.md 2.3 KB
- references/phase4-synthesis-deep-dive.md 2.6 KB
- references/regression-questions.md 11 KB
- references/script-integration-framework.md 17 KB
- references/script-patterns-catalog.md 21 KB
- references/skill-development-conventions.md 4.7 KB
- references/specification-template.md 16 KB
- references/synthesis-protocol.md 18 KB
- scripts/_constants.py 2.9 KB runs code
- scripts/check_docs_safety.py 2.3 KB runs code
- scripts/discover_skills.py 17 KB runs code
- scripts/frontmatter.py 1.1 KB runs code
- scripts/init_skill.py 10 KB runs code
- scripts/package_skill.py 5.9 KB runs code
- scripts/quick_validate.py 13 KB runs code
- scripts/skill_modularity_audit.py 13 KB runs code
- scripts/triage_skill_request.py 30 KB runs code
- scripts/validate-skill.py 31 KB runs code
- TRANSFORMATION_NOTES.md 12 KB
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.
- 3d ago Changed · +7 lines · +25 tokens per session 681bd26efb21
- 9d ago Changed · -12 tokens per session 2f09e7efe5bc
- 18d ago Changed · +1 lines 87698d8fa50c
- 20d ago Changed · -2 tokens per session fec56aed2216
- 22d ago Changed · +5 lines dc011ad3fe3a
- 25d ago Changed · +2 lines 19fc7fca2cab
- 28d ago Changed · +26 tokens per session 0d87bffb31de
- 1mo ago First seen · 326 lines · 115 tokens per session scan A 48f99b914a2a
skillforge is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 152 tokens to every session and 3,777 once invoked, about $0.0006 per session on Opus 5.5. 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 skills, from other repositories
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
review-remote
Review open PR/MR and publish findings.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
azure-devops-automation
CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads.
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.