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.
git clone --depth 1 https://github.com/PraveenJayaprakash-JP/repomemoryWrote 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/praveenjayaprakash-jp/repomemory/deploy)<a href="https://agentmods.dev/commands/praveenjayaprakash-jp/repomemory/deploy"><img src="https://agentmods.dev/badge/commands/praveenjayaprakash-jp/repomemory/deploy/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/commands/praveenjayaprakash-jp/repomemory/deploy"><img src="https://agentmods.dev/badge/commands/praveenjayaprakash-jp/repomemory/deploy.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 | $0.00000 | $0.01290 |
| Opus 5.5 | $0.00000 | $0.00516 |
| Sonnet 5.5 | $0.00000 | $0.00258 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
deploy 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 1mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
---
trigger: /deploy [environment]
title: Deployment Checklist
description: |
Run a production-ready deployment workflow with pre-checks, build verification,
environment validation, platform-aware deployment, and post-deploy verification.
Supports `--dry-run` to check without deploying and `--force` to skip non-critical steps.
parameters:
- name: environment
description: Target deployment environment (e.g., staging, production). If omitted, defaults to production.
required: false
- name: dry-run
description: Perform all checks but do not execute the actual deployment.
type: boolean
default: false
- name: force
description: Skip non-critical checks (e.g., bundle size warnings, minor test failures). Use with caution.
type: boolean
default: false
---
Deployment Workflow
Target environment:
{{environment | default('production')}}
Dry-run:{{dry-run | default(false)}}
Force mode:{{force | default(false)}}
1. Pre-Deploy Checks
- Tests pass: Run the project’s test suite (e.g.,
npm test,pytest,go test ./...).
If tests fail and--forceis not set → abort. If--forceis set → warn and continue. - No uncommitted changes:
git status --porcelainshould be empty.
If dirty → abort (unless--forceis set, then stash or warn). - Branch is up-to-date:
git fetch origin && git status -sbshowsaheadonly if you have local commits you intend to push.
If behind → abort (merge/rebase first).
2. Build Verification
- Production build succeeds: Run the build command (
npm run build,vite build,docker build …, etc.).
If it fails → abort (even with--force). - Bundle size within limits: Check the output size of assets.
If size exceeds project-specific thresholds (e.g., >300 kB gzipped for JS) → warn.
If--forceis set → skip this warning, otherwise prompt for confirmation. - No new warnings/errors: Review build output for any unexpected warnings.
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.
- 1mo ago First seen · 112 lines · 0 tokens per session scan A 54f61f122e68
deploy is a command published in the GitHub repository PraveenJayaprakash-JP/repomemory (1 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,290 tokens. 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
sre
You are a battle-hardened SRE specialist. You design for failure, respond to incidents with calm precision, define meaningful SLOs, and build systems that degrade gracefully instead of catastrophically. You have zero tolerance for "it works on my machine" or "we'll add monitoring later.".
debug
Systematic debugging with hypotheses and evidence gathering.
improve
/improve Scan and fix all improvement categories /improve arch Architectural improvements only /improve duplication Duplicate code / abstraction consolidation /improve quality Code quality (GuardLoop patterns GL-01 through GL-10) /improve security Security posture improvements /improve --dry-run Show what would be…
tester
You are an exacting senior software tester — a quality gatekeeper who assumes code fails until proven otherwise. You find the failure cases others miss, never accept vague assurances, and never let gaps in test coverage slide.
testloop
Role: Autonomous quality enforcement engine. You run tests, parse results, route failures to the coder for targeted fixes, and loop until the implementation is clean or the iteration budget is exhausted. You never accept "it should work" — only green tests.
auto
You are the Auto Pilot, the master orchestrator that coordinates the entire development pipeline automatically. The user speaks once, you handle everything else.