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.
git clone --depth 1 https://github.com/zakelfassi/skills-driven-developmentWrote 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/commands/zakelfassi/skills-driven-development/forge)<a href="https://agentmods.dev/commands/zakelfassi/skills-driven-development/forge"><img src="https://agentmods.dev/badge/commands/zakelfassi/skills-driven-development/forge/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/commands/zakelfassi/skills-driven-development/forge"><img src="https://agentmods.dev/badge/commands/zakelfassi/skills-driven-development/forge.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 | $0.00020 | $0.00530 |
| Opus 5.5 | $0.00008 | $0.00212 |
| Sonnet 5.5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
forge 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 1mo 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge
You are being asked to forge a new skill as part of a Skills-Driven Development workflow.
What the user typed
/forge $ARGUMENTS
Your task
- Parse
$ARGUMENTS. The first whitespace-delimited token is the skill name. Everything after--(if present) is an optional description. Examples:/forge deploy-preview→ name =deploy-preview, no description yet/forge deploy-preview -- Deploy the current branch to staging for review→ name =deploy-preview, description =Deploy the current branch to staging for review
- Validate the name against the Agent Skills spec:
- Lowercase alphanumeric and hyphens only
- 1-64 characters
- Must not start or end with a hyphen; must not contain
--(unless used as the description separator) - If invalid, tell the user exactly what's wrong and stop.
- Load the skillforge skill (
skdd-claude:skillforge, or the project-scopeskillforgeif present). Follow its steps literally:- Ask the user for inputs you don't have (description, triggers, steps, conventions, edge cases) — do not fabricate.
- Write the new
SKILL.mdto.claude/skills/<name>/SKILL.md. - Append a row to
.skills-registry.mdat the project root. - Update
.skills-registry.jsontoo if it exists.
- When done, summarize in one paragraph:
- Where the skill was written
- What the registry now contains
- What the next session will see
Rules
- Never skip the registry update. A forged skill that isn't registered is invisible to future agents.
- Never fabricate steps for the skill body. Ask the user if you don't know.
- Always include trigger language in the description (
Use when …) so future sessions can discover the skill. - Prefer updating an existing skill over forging a new similar one. If a skill with the same name already exists, stop and ask the user whether to update it instead.
After forging, suggest the user commit the new skill (git add .claude/skills/<name> .skills-registry.md && git commit -m "forge: <name>").
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.
- 1mo ago First seen · 44 lines · 20 tokens per session scan A 33ad5242388d
forge is a command published in the GitHub repository zakelfassi/skills-driven-development (18 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 530 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
cc-stack
(Conductor) Detect the project stack and write commands + a generated ruleset into CLAUDE.md.
cc-review
(Conductor) Review code changes against spec and standards.
cc-debug
(Conductor) Systematically diagnose and fix a bug.
cc-docs
(Conductor) Audit and update project documentation.
cc-test
(Conductor) Analyze coverage gaps and write missing tests.
cc-refactor
(Conductor) Refactor a file or module for clarity and simplicity.