Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rajdeepratan/SlashForgenpx agentmods add skills/rajdeepratan/slashforge/add-commandWrote 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/rajdeepratan/slashforge/add-command)<a href="https://agentmods.dev/skills/rajdeepratan/slashforge/add-command"><img src="https://agentmods.dev/badge/skills/rajdeepratan/slashforge/add-command/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/rajdeepratan/slashforge/add-command"><img src="https://agentmods.dev/badge/skills/rajdeepratan/slashforge/add-command.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 | $0.00039 | $0.00705 |
| Opus 5.5 | $0.00016 | $0.00282 |
| Sonnet 5.5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
add-command 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a command or discipline skill
The kit ships two kinds of invocable template, both living in
templates/slashforge/<name>.md and both installed as slashforge-<name> on
every host:
- Commands (
COMMAND_FILES) — the entry points a user types:setup,code,investigate,fix,resume,review-pr,test,refactor. These drivemeta.json'scommandslist and thestatusoutput. - Discipline skills (
SKILL_FILES) — disciplines the workflow invokes on the user's behalf:brainstorm,plan,debug,tdd,verify,request-review,review-feedback,worktree,parallel. Kept out ofCOMMAND_FILESon purpose sostatusreports only what users actually type.
Before starting
Read .claude/rules/templates.md and .claude/rules/cli.md. Decide first: is this
a user entry point (command) or an internal discipline (skill)? That decides which
array it goes in.
Steps
- Create
templates/slashforge/<name>.mdwith frontmatter (name,description) and body ≤ 200 lines (≤ 500 if authored as a skill). Use target blocks for host-specific wording — a command often needs aclaudevsagentssplit for how it dispatches reviewers/PRs. - Register it in
bin/install.js: addpath.join('slashforge', '<name>.md')toCOMMAND_FILES(user command) orSKILL_FILES(discipline). Do not put it in both. - Wire references — if it's a command, reference it from
CLAUDE.md's orchestration table and any workflow guide that hands off to it. If it's a discipline, make sure the phase that invokes it names it. - Run tests —
npm test(spec-features.test.jsasserts that shipped commands install correctly). - Regenerate the snapshot and review:
node scripts/snapshot-claude-render.js git diff test/fixtures/claude-render - Update
CHANGELOG.mdunder## [Unreleased]. If it's a new user command, it will also surface inmeta.json'scommands— mention it in the docs site.
Verify
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 Changed 63f13fb3836d
- 7d ago First seen · 45 lines · 39 tokens per session scan A fec2d3702570
add-command is a skill published in the GitHub repository rajdeepratan/SlashForge (5 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 705 once invoked, about $0.0002 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 2026-10-09.
Other skills, from other repositories
openclaw-github-repo-commander
7-stage super workflow for GitHub repo audit, cleanup, PR review, and competitor analysis.
Git Workflow
Use this skill when you want a clean Git history (easy reviews, easy rollbacks) and consistent PR hygiene—especially when an agent is helping you make changes across multiple files.
verify-change
A change-checking skill that reviews code differences and checks whether related documentation, tests, and records were updated.
verify-module
A module-checking skill that scans a project’s folders, code, and documentation. It expects each module to include a README.md and DESIGN.md, which explain how the module is used and why it was designed that way.
verify-quality
A code-quality checker that measures complexity, size, naming, and common code smells. It reports problems such as duplicated code, unused code, and overly long functions.
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.