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 instructions/malekyala/yala-agentic-toolkit/agents-mdgit clone --depth 1 https://github.com/MalekYala/yala-agentic-toolkitWrote 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/malekyala/yala-agentic-toolkit/agents-md)<a href="https://agentmods.dev/instructions/malekyala/yala-agentic-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/malekyala/yala-agentic-toolkit/agents-md.svg" alt="Measured on agentmods" 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 | $0.03290 | $0.03290 |
| Opus 5 | $0.01645 | $0.01645 |
| Sonnet 5 | $0.00658 | $0.00658 |
| Haiku 4.5 | $0.00329 | $0.00329 |
Grade A, and why
yala-agentic-toolkit 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 4d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — using yala-toolkit from a coding-harness agent
529 standalone Python/Go/Bash/TS utilities for system, network, security, AI, infra, and dev work. This file is the routing table; everything else is discoverable at runtime.
Setup (once per checkout)
python -m venv .venv && source .venv/bin/activate
pip install -e . # slim base; extras: .[browser], .[crawl], .[voice], .[db], .[crypto], .[all]
Discovery — do NOT read category READMEs (they cost thousands of tokens)
yala find <task words> # top ~10 matching tools, one-liners (cheapest, start here)
yala find <query> --json # same, machine-readable
yala info <tool> # tool's docstring + exact run command
yala list <category> # tools in one category
cat tools/data/manifest.json # full manifest: every tool + mutates/json_output/flags
Invocation
yala <category> <tool> [args...] # preferred; tool names are hyphenated
yala <tool> [args...] # works when the name is unique
python src/<category>/<tool>.py … # direct invocation always works too
Conventions contract (rely on these)
- Every tool supports
--help;yala <cat> <tool> --helpforwards to it. - Mutating tools support
--dry-run("mutates": truein the manifest). Always dry-run first when changing files/state. - Data-producing tools generally support
--json("json_output": truein the manifest) — prefer it for parsing. - Secrets come from environment variables only, never CLI args.
- Exit codes:
0success,1finding/failure (scanners exit 1 when they find something — that is not a crash),2usage error. - Dual-use tools (
network-recon,network-tunneling,api-toolshardening,sqli-defenseprobes, load testing) are authorized-use only — targets must be owned or explicitly authorized.
Category routing table
| Category | Use it for |
|---|---|
system-process |
CPU/mem/disk diagnostics, process + service management |
file-data |
organize, dedupe, rename, sync, back up, convert files |
compression |
codec benchmarks, archives, lossless recompress |
security |
secret scanning, CVE checks, file integrity, permissions |
sqli-defense |
SQL-injection source/log scanning + prevention |
ai-detection |
C2PA/provenance + heuristics for AI-made content |
antivirus |
static triage, signature scan, quarantine, ClamAV |
crypto |
AEAD file encryption, TRNG keys, PGP |
vault |
Vault AppRole, unseal, backup/restore, rotation |
config-secrets |
layered config render/validate/diff, .env hygiene, rotation |
network |
DNS, TLS expiry, ports, bandwidth (authorized hosts) |
network-recon |
port scan, host discovery (owned networks ONLY) |
network-tunneling |
SSH tunnels, proxies, WireGuard configs |
ssh |
config lint, known_hosts/authorized_keys hygiene, exec |
development |
git helpers, TODO extraction, license/dep checks |
github / gitlab |
PR/MR triage, pipelines, releases, security alerts |
cicd |
lint/generate/run pipelines, semver, changelog, deploy gates |
nextjs / react-dev / component-libs |
JS stack bootstrap, audits, codegen |
code-intelligence |
gitnexus/codegraph reports: hotspots, impact, arch |
coding-loops |
iterate-until-goal loops (coverage, CVEs, flaky tests) |
agent-loops |
ReAct/plan-execute/reflexion/RAG agent patterns (LLM API) |
llm-tuning |
prompt A/B, param sweeps, eval harnesses (Ollama) |
deep-research |
multi-source cited research report agent |
web-search |
SearXNG search/crawl |
crawlee |
resilient crawlers, SEO audits, sitemaps |
browser-automation |
Playwright: screenshots, link checks, form smoke tests |
libretto |
Libretto TS workflows: sessions, harvest, network capture |
nl2sql |
plain-English → safe read-only PostgreSQL |
database / db-migrations |
PG/SQLite DBA dashboards, schema diff, migration runner |
redis / message-queue / messaging-streams |
Redis/RabbitMQ/Streams/Kafka ops |
api-tools / api-docs / api-versioning / api-gateway |
probe/lint/harden APIs, OpenAPI gen, versioning, gateway |
rate-limiting |
limiter algorithms, Redis limiter, enforcing proxy |
webhooks |
HMAC sign/verify, receiver, delivery, replay, relay |
feature-flags |
flag engine, A/B stats, rollouts, hygiene audit |
observability / dashboards-alerting |
traces, Prometheus, SLO monitors, dashboards |
logging |
JSON logs, parse/query/aggregate, redact, ship, alert |
load-testing |
HTTP load gen, benchmarks, soak tests, regression gates |
chaos-engineering |
fault injection, resilience experiments |
iac-provisioning / kubernetes |
Terraform/Ansible, k8s manifests/ops |
cloud-cost |
cost/billing analysis and optimization |
backup-dr |
backup, restore, disaster recovery drills |
data-pipeline |
ETL/orchestration helpers |
progressive-delivery |
canary/blue-green release automation |
local-environment |
dev-service dashboards, repo health, Obsidian, nginx |
gpu-stack |
NVIDIA GPU/CUDA, Ollama/LiteLLM health |
go-tools |
Go hardware (I2C/GPIO/serial) + Go toolchain wrappers |
jq |
advanced jq JSON wrangling recipes |
bash |
certs, disk/mem alerts, service waits, backups |
document-conversion |
any document → Markdown |
streaming |
capture/transcribe .m3u8 streams |
audio-voice |
Whisper transcription, diarization, voice ID |
localization |
i18n string extract/translate/validate/merge |
market-data |
stocks/crypto prices, alerts (read-only) |
news-trends |
news digests, trend snapshots |
messaging |
email via SMTP, SMS/calls via Twilio-compatible API |
vector-pageindex |
vector DB + page-index tools (local embeddings) |
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.
- 4d ago First seen · 219 lines · 3,290 tokens per session scan A 74c88ee67527
yala-agentic-toolkit AGENTS.md is an instructions file published in the GitHub repository MalekYala/yala-agentic-toolkit (0 stars, last pushed 15d ago), licensed MIT. It adds 3,290 tokens to every session, about $0.0164 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.