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-repairgit clone --depth 1 https://github.com/kernalix7/AIPSWrote 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/commands/kernalix7/aips/aips-repair)<a href="https://agentmods.dev/commands/kernalix7/aips/aips-repair"><img src="https://agentmods.dev/badge/commands/kernalix7/aips/aips-repair.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 | $0.00020 | $0.00617 |
| Opus 5 | $0.00010 | $0.00309 |
| Sonnet 5 | $0.00004 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
aips-repair scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aips:repair
Force the repair path of /aips:init (CASE D). Useful when .priv-storage/ is partially present, root symlinks are broken, or the auto-detector would otherwise pick a different case. Non-destructive — only adds back what is missing.
What it does
- Locate
PROJECT_ROOT— walk up from$PWDto nearest.git. - Enumerate missing or broken — check each managed asset and flag it as
missing,broken-symlink, orok:.priv-storage/CLAUDE.md.priv-storage/WORK_STATUS.md.priv-storage/memory/MEMORY.md+ starter category files.priv-storage/sessions/directory- Root symlinks:
CLAUDE.md,AGENTS.md,.cursorrules,.vscode/settings.json(must resolve into.priv-storage/) tmp-igbkp/*.sh(the 9 toolkit scripts) — must exist and be+x.gitignoreAIPS block (marker comment + required entries)
- Restore missing items from
templates/— only items flaggedmissingorbroken-symlink. Never overwrite an existing file with template content. For broken symlinks, remove the dangling link first, then recreate. - Re-
chmod +xany toolkit script that exists but lost its executable bit. - Patch
.gitignoreidempotently if the AIPS block is missing. - Verify — run
lib/verify-init.shand report PASS/FAIL.
What it never does
- Never overwrite
.priv-storage/CLAUDE.md,WORK_STATUS.md,memory/*.mdcontent, orsessions/*when they already exist. - Never delete project source code or anything outside
.priv-storage/,tmp-igbkp/, and the four root symlink paths. - Never run the migration logic from CASE B (use
/aips:migrate-from-mdfor that). - Never run the fresh-init logic from CASE A — repair only restores what is missing.
Output
[repair] target <PROJECT_ROOT>
[repair] missing 3 items — .priv-storage/memory/MEMORY.md, root .cursorrules, tmp-igbkp/archive.sh
[repair] broken symlinks 1 item — root AGENTS.md (dangling)
[repair] restored 4 items
[repair] gitignore ok (block present)
[repair] verify PASS
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.
- 5d ago First seen · 43 lines · 20 tokens per session scan A ba258f0c7989
aips-repair is a command published in the GitHub repository kernalix7/AIPS (5 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 617 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 2026-08-31.
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.