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 skills add jmagly/aiwg --skill soul-disablegit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/soul-disable)<a href="https://agentmods.dev/skills/jmagly/aiwg/soul-disable"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/soul-disable/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/jmagly/aiwg/soul-disable"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/soul-disable.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 69 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Agent Snooping · line 78 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00015 | $0.01100 |
| Opus 5 | $0.00008 | $0.00550 |
| Sonnet 5 | $0.00003 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
soul-disable 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 7d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Soul Disable
You are a Soul Management Specialist responsible for disabling SOUL.md enforcement.
Your Task
Remove the soul directive from platform context file(s) and remove the enforcement rule so SOUL.md is NOT loaded at the next session start. The SOUL.md file itself is preserved on disk — no content is lost.
Parameters
| Flag | Description |
|---|---|
--provider <name> |
Target specific provider: claude, warp, copilot, cursor, factory, windsurf, opencode, codex |
--all |
Disable for all installed providers (default if no provider specified) |
Workflow
Step 1: Determine Target Providers
If --provider <name> specified, operate on that provider only.
If --all or no flag, detect installed providers by checking for their context files.
Step 2: Check Current State
For each target provider:
- Check if the context file exists
- Check if the
@SOUL.mddirective is currently present
# Example for Claude Code
grep -q "@SOUL.md" CLAUDE.md && echo "enabled" || echo "already disabled"
Step 3: Remove Directive
For @-link style (Claude, Warp, Windsurf, Copilot, Cursor, Factory, OpenCode):
Remove the @SOUL.md line from the context file. Preserve all surrounding content.
For Codex (inline injection):
Remove the block between soul injection markers:
<!-- BEGIN SOUL -->
...content...
<!-- END SOUL -->
Step 4: Remove Enforcement Rule
# Remove the enforcement rule
rm -f .claude/rules/soul-enforcement.md
Step 5: Revert Agent Soul Wiring (if present)
Check if any agent definitions have soul identity sections added by soul-enable --agents. If found, remove them:
# Check for soul-wired agents
grep -rl "See @.*\.soul\.md" .claude/agents/ 2>/dev/null
Remove the ## Identity section that references the soul file from each wired agent.
Step 6: Verify SOUL.md is Preserved
After removing directives and rule, confirm the soul file still exists:
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.
- 7d ago First seen · 168 lines · 15 tokens per session scan A 1dcdcf44eff8
soul-disable is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,100 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 2026-09-05.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
horizon
Run a durable Horizon workflow for a multi-feature goal with bounded autonomous retries and an audit trail.
check-in
Record a Parallax protocol checkpoint with concrete evidence before gated implementation work.
debug
Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.
hyperplan
Harden a non-trivial plan through a three-round adversarial critique and evidence-based synthesis.