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-realigngit 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-realign)<a href="https://agentmods.dev/skills/jmagly/aiwg/workspace-realign"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/workspace-realign/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-realign"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/workspace-realign.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 293 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 367 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.
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 | $0.00019 | $0.02650 |
| Opus 5.5 | $0.00008 | $0.01060 |
| Sonnet 5.5 | $0.00004 | $0.00530 |
| Haiku 4.5 | $0.00002 | $0.00265 |
Grade A, and why
workspace-realign 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 1mo 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Realign
Analyze and reorganize documentation in .aiwg/ to ensure it accurately reflects the current project state, plans, and reality. Uses git commit history to understand changes since documentation was last updated.
Parameters
| Flag | Description |
|---|---|
project-directory |
Project root (default: .) |
--archive-stale |
Move stale documents to .aiwg/archive/ instead of deleting |
--delete-stale |
Delete stale documents (requires confirmation) |
--dry-run |
Preview changes without modifying files |
--since <commit> |
Analyze changes since specific commit (default: last doc update) |
--interactive |
Prompt for each decision |
Execution Steps
Step 1: Analyze Current State
Scan .aiwg/ directory structure:
# Count documents by category
find .aiwg -name "*.md" -type f | wc -l
# Get last modification times
find .aiwg -name "*.md" -type f -exec stat -c '%Y %n' {} \; | sort -rn
Report current state:
Workspace Analysis
==================
Total documents: 47
Categories:
- requirements/ 12 docs
- architecture/ 8 docs
- planning/ 6 docs
- risks/ 4 docs
- testing/ 5 docs
- security/ 3 docs
- working/ 9 docs (temporary)
Step 2: Identify Last Documentation Alignment
Find when documentation was last synchronized with code:
-
Check for alignment marker:
cat .aiwg/.last-alignment 2>/dev/null -
Check git log for doc commits:
git log --oneline --since="30 days ago" -- .aiwg/ -
Find most recent doc update:
git log -1 --format="%H %ci" -- .aiwg/
Report:
Last Alignment
==============
Last doc commit: abc1234 (2025-12-01)
Current HEAD: def5678
Commits since: 23 commits
Days since: 8 days
Step 3: Analyze Code Changes Since Last Alignment
Compare code changes vs documentation:
# Get changed files since last alignment
git diff --name-only <last-alignment-commit>..HEAD
# Categorize changes
git diff --stat <last-alignment-commit>..HEAD
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.
- 1mo ago First seen · 402 lines · 19 tokens per session scan A 4c784507c485
workspace-realign is a skill published in the GitHub repository jmagly/aiwg (225 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 2,650 once invoked, about $0.0001 per session on Opus 5.5. 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
launch
Planning releases and reporting delivery work from GitHub PR history. Use when versioning, CHANGELOGs, rollout or rollback plans, engineering metrics, retrospectives, or stakeholder reports are needed.
pdm
Navigating delivery status read-only: reconciles planned scope (specs/roadmap/PRD) against implemented code for what's built vs left. Not for priority scoring (Rank) or AC conformance (Attest).
sherpa
Guiding workflows by decomposing complex tasks (Epics) into Atomic Steps under 15 minutes each, with progress tracking and drift prevention. Use when complex decomposition is needed.
rank
Quantifying priority by scoring competing items with ICE/RICE/WSJF/MoSCoW/Cost of Delay/Kano. No code. Use to prioritize features/bugs/initiatives or arbitrate Must vs Should at MVP scoping.
spark
Proposing new features leveraging existing data/logic as Markdown specifications. Use when brainstorming new features, product planning, or feature proposals are needed. Does not write code.
missive
Invoke only when spawning a quest from a GitHub issue reference. Fetches GitHub issue context for quest spawning. Parses issue references, retrieves structured data via gh, and produces branch suggestions and PR keywords. Used standalone or as input to quest orchestration.