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/brian-lai/para-programming-plugin/archivenpx skills add brian-lai/para-programming-plugin --skill archivegit clone --depth 1 https://github.com/brian-lai/para-programming-pluginWhat 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 | $0.00574 |
| Opus 5 | $0.00008 | $0.00287 |
| Sonnet 5 | $0.00003 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
archive 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archive the current context to create a clean slate for the next task.
Usage
/para:archive
/para:archive --fresh # Completely empty context
/para:archive --seed # Carry forward relevant context
Default: create fresh context with reference to completed summaries.
What It Does
- Read
context/context.mdand extract worktree metadata (worktree_path, or per-phaseworktree_pathentries for phased plans) - Clean up worktrees:
- For each
worktree_pathfound in metadata, rungit worktree remove {worktree_path} - If the worktree has uncommitted changes, warn the user and require them to either commit or stash the changes first, then re-run
/para:archive; do NOT force-remove (this would permanently destroy uncommitted work) - After removal, run
git worktree pruneto clean up stale references - Remove
.para-worktrees/directory if empty
- For each
- Move
context/context.mdtocontext/archives/YYYY-MM-DD-HHMM-context.md - Create a fresh
context/context.mdseeded from../init/context-template.md:
# Current Work Summary
Ready for next task.
---
```json
{
"active_context": [],
"completed_summaries": [
"context/summaries/YYYY-MM-DD-task-name-summary.md"
],
"last_updated": "TIMESTAMP"
}
```
See ../init/context-schema.md for the full field reference.
- Displays: archive location, worktrees removed, confirmation of fresh context, readiness for new task
When to Archive
- Work is complete and summarized
- All tests pass and changes are committed
- Branch has been pushed and PR created (or merged)
- Ready to start a new, unrelated task
Do NOT archive if work is still in progress or you need the current context for continued work.
Recovery
ls -lt context/archives/ # List archives
cp context/archives/2025-11-24-1430-context.md context/context.md # Restore
To restore a worktree after archive (if branch still exists):
git worktree add .para-worktrees/{task-name} para/{task-name}
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 · 78 lines · 15 tokens per session scan A abf430dfc26b
archive is a skill published in the GitHub repository brian-lai/para-programming-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 574 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…