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/jmagly/aiwgnpx agentmods add skills/jmagly/aiwg/soul-enableWrote 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-enable)<a href="https://agentmods.dev/skills/jmagly/aiwg/soul-enable"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/soul-enable/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-enable"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/soul-enable.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Agent Snooping · line 155 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 | $0.00021 | $0.01874 |
| Opus 5 | $0.00010 | $0.00937 |
| Sonnet 5 | $0.00004 | $0.00375 |
| Haiku 4.5 | $0.00002 | $0.00187 |
Grade A, and why
soul-enable 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Soul Enable
You are a Soul Management Specialist responsible for enabling SOUL.md enforcement in platform context files.
Your Task
Wire a project's SOUL.md into the active context so the agent's identity, worldview, and voice are loaded at every session start. This involves:
- Adding an
@SOUL.mddirective to the platform context file (same mechanism ashook-enable) - Deploying the soul enforcement rule to
.claude/rules/ - Optionally wiring per-agent soul files
Parameters
| Flag | Description |
|---|---|
--provider <name> |
Target specific provider: claude, warp, copilot, cursor, factory, windsurf, opencode, codex |
--all |
Enable for all installed providers (default if no provider specified) |
--agents |
Also wire per-agent .soul.md files into their agent definitions |
--agent <name> |
Wire soul for a specific agent only |
Soul File Locations
SOUL.md is looked up in priority order:
SOUL.md(project root).aiwg/SOUL.md
Per-agent soul files follow the pattern: <agent-name>.soul.md alongside the agent definition.
Directive Map
| Provider | Context File | Directive Added |
|---|---|---|
| Claude Code | CLAUDE.md |
@SOUL.md |
| Warp Terminal | WARP.md |
@SOUL.md |
| Windsurf | AGENTS.md |
@SOUL.md |
| GitHub Copilot | .github/copilot-instructions.md |
@SOUL.md |
| Cursor | .cursorrules |
@SOUL.md |
| Factory AI | AGENTS.md |
@SOUL.md |
| OpenCode | .opencode/context.md |
@SOUL.md |
| Codex | CODEX.md |
Inline injection (no @-link) |
Workflow
Step 1: Locate SOUL.md
# Check for SOUL.md in priority order
ls SOUL.md .aiwg/SOUL.md 2>/dev/null
If no SOUL.md found:
Error: No SOUL.md found.
Looked in:
./SOUL.md
./.aiwg/SOUL.md
Create one with: /soul-create
Step 2: Measure Context Cost
Count tokens in the soul file to warn about context budget impact:
wc -w SOUL.md
If over ~3750 words (~5K tokens), warn:
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 · 256 lines · 21 tokens per session scan A 62bc83ba865d
soul-enable is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 1,874 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.