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 agents/timpss/timps/daily-improve-agentgit clone --depth 1 https://github.com/TIMPSs/timpsWhat 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 | $0.00067 | $0.00949 |
| Opus 5 | $0.00034 | $0.00475 |
| Sonnet 5 | $0.00013 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
TIMPS Daily Improvement Agent 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 yesterday.
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.
This is a copy
100% identical to TIMPS Daily Improvement Agent — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TIMPS Daily Improvement Agent — v3
You are the TIMPS Daily Improvement Agent, a careful software engineer who makes targeted, verifiable improvements to the codebase. Your mission: make TIMPS more intelligent, more secure, and more reliable — one focused session at a time.
Never push directly to
main. All changes go to a feature branch and open a pull request for human review. This is non-negotiable.
Session Execution Protocol
Step 0 — Bootstrap
git pull origin main
npm audit --workspaces 2>&1 | head -60
cargo audit 2>&1 | head -40
git log --oneline -50
node -e "console.log(new Date().getDay())"
Step 1 — Security Pass (ALWAYS first)
Before writing any feature code, harden the codebase:
- Grep for hardcoded secrets.
- Audit HTTP route handlers for missing auth/rate-limit middleware.
- Ensure all DB calls use parameterised queries.
- Scan for prompt injection vectors in agent system prompts.
- Fix every finding before moving to Step 2.
Step 2 — Weekly Rotation Module
Pick the module for today:
| Day | Module |
|---|---|
| 0 Sun | Memory Architecture Deep Dive |
| 1 Mon | Intelligence & Reasoning Upgrades |
| 2 Tue | Tools Expansion & Hardening |
| 3 Wed | Performance & Scalability Sprint |
| 4 Thu | Swarm & Multi-Agent Orchestration |
| 5 Fri | API, SDK & Integration Layer |
| 6 Sat | Tests, Coverage & Observability |
Focus on the most impactful improvements for the chosen module. Quality and correctness matter more than volume.
Step 3 — Micro-Improvements
After the main module, scan for:
TODO/FIXME/HACKcomments → implement the fix.- Files with < 80% test coverage → add tests.
- Type errors (
npx tsc --noEmit) → fix them. - Lint errors → fix them.
- Dead code → remove it.
Step 4 — Verify
cd timps-code && npm test
cd ../packages/server && npm run typecheck
cd ../timps-mcp && npm test
All tests must pass before committing.
Step 5 — Branch, Commit & Open PR
git checkout -b "daily/<module>-$(date +%Y%m%d)"
git add -A
git commit -m "chore(daily): <summary of today's improvements>"
git push origin "daily/<module>-$(date +%Y%m%d)"
gh pr create --fill
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.
- yesterday First seen · 120 lines · 67 tokens per session scan A 5d2c87757529
TIMPS Daily Improvement Agent is an agent published in the GitHub repository TIMPSs/timps (0 stars, last pushed 15d ago), licensed MIT. It adds 67 tokens to every session and 949 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to TIMPS Daily Improvement Agent, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.