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 commands/softaworks/agent-toolkit/add-skillgit clone --depth 1 https://github.com/softaworks/agent-toolkitWhat 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 | $0.00011 | $0.02304 |
| Opus 5 | $0.00005 | $0.01152 |
| Sonnet 5 | $0.00002 | $0.00461 |
| Haiku 4.5 | $0.00001 | $0.00230 |
Grade A, and why
add-skill 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 yesterday.
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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Skill
Copy a skill from a source path to the project, verify naming consistency, and generate README.md if missing.
Usage
/add-skill <source-path>
Arguments:
<source-path>- Path to the skill directory to add (required)
Examples:
/add-skill ~/.claude/skills/my-skill
/add-skill ~/workspace/other-project/skills/awesome-skill
/add-skill /home/leo/workspace/softaworks/projects/claude-plugins/plugins/planning/skills/spec-interview
Workflow
1. Validate Source Path
Check that the source path exists and is a directory:
if [ -d "<source-path>" ]; then
echo "Source path exists"
else
echo "Error: Source path does not exist or is not a directory"
exit 1
fi
If source path is invalid, stop and report the error to the user.
2. Extract Skill Name
Get the skill name from the source path (basename of the directory):
basename <source-path>
Example: /path/to/my-skill → my-skill
Store this as the skill name for the rest of the workflow.
3. Copy Skill to Project
Copy the entire skill directory to skills/:
cp -r <source-path> skills/
Report to user: "✅ Copied skill to skills/[skill-name]"
4. Verify Folder Name is Kebab-Case
Check that the folder name follows kebab-case convention:
- Only lowercase letters, numbers, and hyphens
- No underscores, spaces, or uppercase letters
Regex pattern: ^[a-z0-9]+(-[a-z0-9]+)*$
Use Bash to check:
skill_name="[skill-name]"
if [[ $skill_name =~ ^[a-z0-9]+(-[a-z0-9]+)*$ ]]; then
echo "Folder name is valid kebab-case"
else
echo "Warning: Folder name is not kebab-case"
fi
If invalid, warn the user but continue (we'll check SKILL.md next).
5. Verify SKILL.md Exists and Read Frontmatter
Check for SKILL.md in the copied skill directory:
ls skills/[skill-name]/SKILL.md
If SKILL.md doesn't exist:
- Error and stop: "❌ Error: No SKILL.md found in skills/[skill-name]"
- Suggest: "Please ensure the source directory contains a valid SKILL.md file"
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.
- yesterday First seen · 325 lines · 11 tokens per session scan A d31c0705b005
add-skill is a command published in the GitHub repository softaworks/agent-toolkit (2,401 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 2,304 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
speckit.opsmill.retrospect
Run a session retrospective that surfaces context-management gaps and routes them to approved follow-up actions.
create-issue
Transform feature descriptions, bug reports, or improvement ideas into well-structured GitHub issues.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.