Borrowing it
Nothing to install: this file belongs to husamql3/pstrack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/husamql3/pstrack/stage/AGENTS.mdgit clone --depth 1 https://github.com/husamql3/pstrackWrote 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/instructions/husamql3/pstrack/agents-md)<a href="https://agentmods.dev/instructions/husamql3/pstrack/agents-md"><img src="https://agentmods.dev/badge/instructions/husamql3/pstrack/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/husamql3/pstrack/agents-md"><img src="https://agentmods.dev/badge/instructions/husamql3/pstrack/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.06284 | $0.06284 |
| Opus 5.5 | $0.02514 | $0.02514 |
| Sonnet 5.5 | $0.01257 | $0.01257 |
| Haiku 4.5 | $0.00628 | $0.00628 |
Grade A, and why
pstrack AGENTS.md 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 2mo 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 — 554 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PStrack - App Context
What It Is
PStrack is a competitive programming accountability platform. Users join groups, solve one daily problem from the NeetCode 250 roadmap, and get auto-verified against LeetCode/Codeforces APIs. Points, streaks, and badges create the motivation loop. The tagline: Show up. Solve. Repeat.
Branching
See docs/BRANCHING.md. stage is the default working branch; main is the stable release branch. Start feature and fix branches from stage, and do not push or open pull requests unless explicitly asked.
Core Loop
- Midnight - Trigger.dev cron assigns the next NeetCode 250 problem to all active groups
- User clicks "Mark as Solved"
verify-submissionjob polls LeetCode/Codeforces for an accepted submission matching the problem + timestamp- If found: +10 points, streak incremented, badges evaluated
- If neither solved nor paused by end of day:
mark-missedjob fires → -3 points, streak breaks
User Actions Per Day
| Action | Outcome |
|---|---|
| Solve | +10 pts, +5 if first in group, streak continues |
| Pause | Streak preserved, −5 pts, consumes 1 pause |
| Miss | -3 pts, streak resets |
Points & Gamification
- +10 daily solve, +5 first in group, -3 miss
- Streak multipliers: 7d → 1.2x, 30d → 1.5x (bonus logged separately)
- Badges: Streak 7/30/100, First Solver 10/50, Consistent 30
- Leaderboard: group (all tiers) and global top 100 (Pro only), filterable by week/month/all-time
Tiers
| Free | Pro ($5 one-time) | |
|---|---|---|
| Groups | Join 1 (max 30 members) | Join up to 5 (max 50 members) |
| Private groups | No | Yes (creator perk) |
| Pauses/month | 2 | 4 |
| Global leaderboard | No | Yes |
| Profile badge | No | Yes |
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.
- 2mo ago First seen · 554 lines · 6,284 tokens per session scan A ee4de718f302
pstrack AGENTS.md is an instructions file published in the GitHub repository husamql3/pstrack (119 stars, last pushed 27d ago), licensed MIT. It adds 6,284 tokens to every session, about $0.0251 per session on Opus 5.5. 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.
pstrack AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pstrack AGENTS.mdhusamql3/pstrack | Instructions file | 119 | 27d ago | MIT | A | 6,284 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |