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 agentmods add skills/jmagly/aiwg/validate-addonnpx skills add jmagly/aiwg --skill validate-addongit 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/validate-addon)<a href="https://agentmods.dev/skills/jmagly/aiwg/validate-addon"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/validate-addon.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00015 | $0.01759 |
| Opus 5 | $0.00008 | $0.00879 |
| Sonnet 5 | $0.00003 | $0.00352 |
| Haiku 4.5 | $0.00002 | $0.00176 |
Grade A, and why
validate-addon 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Addon
You check an entire AIWG addon directory for completeness and release readiness, then produce a detailed structured report covering manifest integrity, artifact completeness, placement violations, and any blocking issues.
Triggers
- "validate this addon" → check the addon in the current or named directory
- "is this addon ready to release" → run full release readiness check
- "check the addon" → validate the named addon
- "pre-release check on my addon" → run validate-addon
- "addon readiness report" → full validation with report output
- "validate addon at " → validate the addon at the given path
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| Current directory | "validate this addon" | Validate addon at cwd |
| Named addon | "check the aiwg-dev addon" | Find addon by name and validate |
| Path-specific | "validate addon at agentic/code/addons/my-addon" | Validate at given path |
| Release gate | "is this addon ready to release" | Full validation, block on any FAIL |
| Quick check | "any issues with this addon" | Run validation, summarize findings |
Process
-
Locate the addon:
- If path given: use it
- If name given: find
agentic/code/addons/<name>/manifest.json - If current directory: look for
manifest.jsonin cwd or walk up to nearest addon root
-
Read and validate
manifest.json:- File exists at addon root
- Valid JSON (parseable)
- Required fields present:
id,type,name,version,description typeequals"addon"versionfollows CalVer format (YYYY.M.PATCH, no leading zeros)corefield present (boolean)autoInstallfield present (boolean)- If
devOnly: true: confirm this is intentional (it excludes fromaiwg use all)
-
Check
README.md:- File exists at addon root
- Non-empty content
-
Validate each skill listed in manifest: For each entry in
manifest.jsonskillsarray:skills/<name>/SKILL.mdexistsdescription:frontmatter present# Titlesection present## Behavioror## Processsection present- Collect any missing skills (in manifest but no SKILL.md) and orphaned skills (SKILL.md exists but not in manifest)
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 · 186 lines · 15 tokens per session scan A 874ca9ece48f
validate-addon is a skill published in the GitHub repository jmagly/aiwg (208 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,759 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 2026-08-30.
Other skills, from other repositories
hunt
Compose a guided or automatic shift from the ready catalog, then review it first or run it directly under one time budget. Use when the owner wants to choose jobs or let Nightshift find the highest-value applicable work.
archive
File the finished part of the run state into a dated archive — shipped items, research, opportunities, the rotated journal, and handled snags. The live files stay lean; the facts stay on disk.
doctor
Read-only Nightshift diagnosis — workspace, rules, markers, session, process lease, watchman, deadline, and classified next actions. Use when a shift looks wrong, recovery is unclear, or the owner asks what Nightshift sees. Never repairs by being invoked.
import-issues
Stage explicitly selected GitHub issues onto the drafting table as quoted source. Never searches, never writes back to GitHub, never installs gh.
purge
Permanently delete this project's Nightshift state. Does not uninstall the plugin.
stop
Issue a stop-work order — pause the shift immediately, leaving unfinished items open.