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/mnott/pai/reconstructnpx skills add mnott/PAI --skill reconstructgit clone --depth 1 https://github.com/mnott/PAIWhat 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 | $0.00079 | $0.02080 |
| Opus 5 | $0.00039 | $0.01040 |
| Sonnet 5 | $0.00016 | $0.00416 |
| Haiku 4.5 | $0.00008 | $0.00208 |
Grade A, and why
Reconstruct 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 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.
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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconstruct Skill
USE WHEN user says 'reconstruct sessions', 'rebuild session notes', 'recover session notes', 'retroactively create notes', 'create notes from git history', 'notes are missing', 'backfill session notes', 'reconstruct what we did', OR /reconstruct.
What This Skill Does
Reconstructs session notes for a PAI-registered project by reading:
- Git commit history (authoritative record of what was built)
- JSONL transcripts (user messages reveal intent, decisions, and context)
Generates one session note per day (or per logical session if multiple sessions existed in a day), numbered sequentially from the highest existing note number.
ONLY include what can be verified from git log and JSONL. Never invent or embellish content.
Arguments
| Argument | Default | Description |
|---|---|---|
--days N |
7 | Reconstruct notes for the last N days |
--since YYYY-MM-DD |
— | Reconstruct from this date forward |
--until YYYY-MM-DD |
today | Reconstruct up to this date |
--dry-run |
false | Show what would be created without writing files |
--commit |
false | Git commit the created notes after writing |
Pre-Action Check
Before starting, verify:
- Project is registered: Run
pai project detect(orpai project list) to confirm the current project is known to PAI and get its Notes directory path. - Notes directory exists: The target directory should be
Notes/YYYY/MM/. Create it if absent. - Find highest existing note number: Scan all
Notes/**/*.mdfiles for the pattern^NNNNto find max note number. New notes continue from there. - NEVER overwrite existing notes: If a note file already exists for that date/session, skip it and warn the user.
Step 1 — Find JSONL Files
Claude Code encodes project paths lossily: /, spaces, dots, hyphens all become -. A project may have been accessed from multiple base directories (e.g., ~/Daten/Cloud/Development/ai/PAI and ~/dev/ai/PAI both encode to different paths).
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 · 233 lines · 79 tokens per session scan A 0c09ac7b5386
Reconstruct is a skill published in the GitHub repository mnott/PAI (45 stars, last pushed 8d ago), licensed MIT. It adds 79 tokens to every session and 2,080 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…