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/workspace-healthWrote 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/workspace-health)<a href="https://agentmods.dev/skills/jmagly/aiwg/workspace-health"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/workspace-health/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/workspace-health"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/workspace-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Agent Snooping · line 37 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 178 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00018 | $0.01359 |
| Opus 5 | $0.00009 | $0.00679 |
| Sonnet 5 | $0.00004 | $0.00272 |
| Haiku 4.5 | $0.00002 | $0.00136 |
Grade A, and why
workspace-health 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill access pattern (post-kernel-pivot, 2026.5+)
Skill names referenced in this document are AIWG skills, not slash commands. Most are not kernel-listed and cannot be invoked as
/skill-nameby the platform. Reach them via:aiwg discover "<capability>" aiwg show skill <name>Only kernel-listed skills (
aiwg-doctor,aiwg-refresh,aiwg-status,aiwg-help,use,steward) are directly invokable as slash commands. See skill-discovery rule.
Workspace Health Check Skill
Assesses workspace alignment and suggests cleanup or realignment actions at key transition points.
Kernel Delegation
As of ADR-021,
workspace-healthdelegates structural checks to the semantic memory kernel.
Delegation pattern:
workspace-healthretains its consumer-neutral health-check UX- Runs
memory-lintfor every installed framework in.aiwg/frameworks/registry.json - Aggregates results across all consumers into a unified report
aiwg doctorcontinues to call this skill unchanged
Backward compatibility: No UX changes. Output format unchanged.
@agentic/code/addons/semantic-memory/skills/memory-lint/SKILL.md
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "do I need to realign" → workspace realignment check
- "is my workspace aligned" → alignment status check
- "cleanup recommendations" → workspace prune suggestions
Auto-triggers:
- After phase transition flow commands complete
- After completing major features or intensive processes
Trigger Conditions Reference
This skill is commonly invoked:
- At the end of phase transitions (flow commands)
- After completing major features or intensive processes
- When documentation appears out of sync
- Manually via natural language phrases above
Assessment Checklist
1. Working Directory Health
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 · 194 lines · 18 tokens per session scan A 84587cda9564
workspace-health is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 1,359 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
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
dos-dispatch
Plan and ship the next batch on one lane: run dos-next-up, acquire a lease with dos arbitrate, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with collision safety.
dos-class-cycle
Run one DOS plan-class lifecycle tick from the workspace [lifecycle] table: evaluate declared transitions, have a judge approve/defer them, write gated plan-meta edits, and log the cycle. Use when gardening plan lifecycle classes automatically.
pace-bridge
Use to bridge a confirmed Superpowers/native plan into PACEflow CHG/HOTFIX artifacts, create artifact-writer prompts, and mark the specific plan as synced.
task-copilot
Use when work should be tracked with tc, including creating PRDs, tasks, handoffs, logs, and work products, or when preserving detailed outputs outside the chat context.