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 workspace-prune-workinggit 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/workspace-prune-working)<a href="https://agentmods.dev/skills/jmagly/aiwg/workspace-prune-working"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/workspace-prune-working/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-prune-working"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/workspace-prune-working.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 265 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 Tool Misuse · line 266 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.
- medium Excessive Agency · line 22 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 | $0.00023 | $0.02746 |
| Opus 5 | $0.00012 | $0.01373 |
| Sonnet 5 | $0.00005 | $0.00549 |
| Haiku 4.5 | $0.00002 | $0.00275 |
Grade A, and why
workspace-prune-working 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 4d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Prune Working
Clean up the .aiwg/working/ directory by intelligently handling temporary files. Promotes valuable content to the main documentation structure, archives content worth preserving, and deletes truly temporary files.
Parameters
| Flag | Description |
|---|---|
project-directory |
Project root (default: .) |
--promote-all |
Promote all promotable files without prompting |
--archive-all |
Archive all archivable files without prompting |
--delete-all |
Delete all deletable files without prompting |
--dry-run |
Preview changes without modifying files |
--interactive |
Prompt for each file decision |
--force |
Skip confirmation prompts |
Purpose of .aiwg/working/
The .aiwg/working/ directory is designated for:
- Multi-agent work-in-progress drafts
- Temporary scratch files during orchestration
- Review feedback before synthesis
- Iterative document versions
It is NOT a permanent storage location. Files here should eventually be:
- Promoted → Moved to appropriate
.aiwg/subdirectory as finalized docs - Archived → Preserved in
.aiwg/archive/for historical reference - Deleted → Removed when no longer useful
Execution Steps
Step 1: Scan Working Directory
Inventory all files in .aiwg/working/:
# List all files with metadata
find .aiwg/working -type f -exec stat -c '%Y %s %n' {} \; | sort -rn
# Count by subdirectory
find .aiwg/working -mindepth 1 -maxdepth 1 -type d | while read dir; do
echo "$(basename "$dir"): $(find "$dir" -type f | wc -l) files"
done
Report:
Working Directory Scan
======================
Total files: 23
Total size: 145 KB
By Category:
architecture/ 8 files (SAD drafts, reviews)
requirements/ 5 files (UC iterations)
testing/ 4 files (test plan drafts)
scratch/ 6 files (temporary notes)
Age Distribution:
< 1 day: 4 files
1-7 days: 8 files
> 7 days: 11 files
Step 2: Classify Files
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.
- 4d ago First seen · 369 lines · 23 tokens per session scan A 731f6af28d06
workspace-prune-working is a skill published in the GitHub repository jmagly/aiwg (210 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 2,746 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.