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 commands/kernalix7/aips/aips-updategit clone --depth 1 https://github.com/kernalix7/AIPSWhat 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 | $0.00014 | $0.00496 |
| Opus 5 | $0.00007 | $0.00248 |
| Sonnet 5 | $0.00003 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade B, and why
aips-update scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Capture the new version reported by `cat ~/.claude/plugins/AIPS/.claude-plugin/plugin.json | grep version`. What it actually says
/aips:update
Pull the latest global plugin release and reconcile the current project's per-project files against the new templates. Non-destructive — preserves user content.
What it does
-
Global plugin update — invoke the plugin update flow:
claude --print "/plugin update AIPS@AIPS"Capture the new version reported by
cat ~/.claude/plugins/AIPS/.claude-plugin/plugin.json | grep version. -
Per-project re-init (CASE C) — re-run
/aips:initsemantics in idempotent-sync mode:- Diff global
templates/against project.priv-storage/managed files. - Apply non-destructive updates only (skeleton headers, toolkit scripts, symlinks,
.gitignoreblock). - Re-render
.priv-storage/CLAUDE.mdfromtemplates/CLAUDE.md.tmplONLY if the template version is newer AND the project CLAUDE.md has no local edits beyond Section 1-7 + 11 placeholders. Otherwise skip and emit a WARN telling the user to merge manually. - Refresh
tmp-igbkp/*.shtoolkit scripts that match the shipped versions verbatim.
- Diff global
-
Memory sync — if agentmemory plugin is installed and the service is reachable, run a one-shot sync pass so per-project
.priv-storage/memory/*.mdand the global agentmemory store stay aligned (dual-write reconciliation). -
Report — emit one line per change:
update: plugin AIPS v<old> → v<new>update: templates synced — <N> files updated, <M> preservedupdate: CLAUDE.md re-renderedORupdate: CLAUDE.md skipped (local edits — merge manually)update: memory synced — <N> entries reconciled(if agentmemory present)
Rules
- Never overwrite
WORK_STATUS.md,memory/*.mdcontent,sessions/*. - Never touch project source code.
- If global plugin update fails, abort and surface the error — do not run per-project sync against stale templates.
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.
- 2d ago First seen · 37 lines · 14 tokens per session scan B 720c01bf6b77
aips-update is a command published in the GitHub repository kernalix7/AIPS (5 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 496 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.