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 skills add congvmit/awesome-llm-token-reduction --skill awesome-list-curatorgit clone --depth 1 https://github.com/congvmit/awesome-llm-token-reductionWrote 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/skills/congvmit/awesome-llm-token-reduction/awesome-list-curator)<a href="https://agentmods.dev/skills/congvmit/awesome-llm-token-reduction/awesome-list-curator"><img src="https://agentmods.dev/badge/skills/congvmit/awesome-llm-token-reduction/awesome-list-curator/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/skills/congvmit/awesome-llm-token-reduction/awesome-list-curator"><img src="https://agentmods.dev/badge/skills/congvmit/awesome-llm-token-reduction/awesome-list-curator.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 | $0.00121 | $0.01165 |
| Opus 5 | $0.00060 | $0.00583 |
| Sonnet 5 | $0.00024 | $0.00233 |
| Haiku 4.5 | $0.00012 | $0.00117 |
Grade A, and why
awesome-list-curator 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 12d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Awesome List Curator
Turn a topic into a high-quality, well-formatted awesome list and ship it to GitHub.
When to Use
- Bootstrapping a new
awesome-<purpose>repo (no README yet). - Finding new tools/libraries/papers/datasets to add to an existing list.
- Auditing a list for dead links, duplicates, or inconsistent formatting.
- Preparing a clean PR that follows the awesome-list conventions.
Inputs to Confirm First
Before researching, establish:
- Purpose — the exact topic/scope (e.g. "techniques and tools that reduce LLM token usage").
- Categories — the top-level sections (see format spec). If unknown, propose 4–8 categories from initial research and confirm.
- Inclusion bar — minimum quality (e.g. maintained in last 12 months, >100 stars, peer-reviewed, or "notably influential"). Default bar in format spec.
- Repo target — owner/name and whether you are adding to your own repo (push) or contributing upstream (fork + PR).
Procedure
1. Plan the taxonomy
- Run 2–4 broad discovery queries to learn the landscape (see discovery sources).
- Draft the category tree. Keep categories mutually exclusive and collectively exhaustive.
- Confirm categories with the user before deep research — re-categorizing later is expensive.
2. Discover candidates
- Work one category at a time. For each, query across all four source types in parallel: web search/fetch, GitHub repo search, arXiv, and cross-referencing peer awesome lists.
- Capture for every candidate: name, canonical URL, one-line description, signal (stars/date/citations), category.
- Collect generously now; filter in the next step. See discovery sources for query patterns.
3. Evaluate and filter
- Apply the inclusion bar. Drop anything unmaintained, broken, off-topic, or a near-duplicate.
- Prefer the canonical/original source over mirrors and aggregators.
- Verify each surviving URL resolves (the publish step also runs check-links.sh).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 91 lines · 121 tokens per session scan A 05539624aafc
awesome-list-curator is a skill published in the GitHub repository congvmit/awesome-llm-token-reduction (6 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 121 tokens to every session and 1,165 once invoked, about $0.0006 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
jira-cli
Interact with Jira from the command line to create, list, view, edit, and transition issues, manage sprints and epics, and perform common Jira workflows. Use when the user asks about Jira tasks, tickets, issues, sprints, or needs to manage project work items.
azure-prices
Look up and compare Azure service pricing using the Azure Retail Prices API. Use this skill whenever the user asks about Azure costs, pricing, rates, or wants to compare prices across regions or services — even if they don't say "pricing" explicitly. Trigger for questions like "how much does a D2 v2 VM cost?"…
calculator
Performs arbitrary-precision arithmetic calculations including addition, subtraction, multiplication, division, and exponents. Use when the user asks to calculate, compute, or evaluate math expressions, or when precise decimal arithmetic is needed to avoid floating-point errors.
az-cli
Use the Azure CLI (az) to manage Azure resources from the command line. Trigger this skill whenever the user asks to create, configure, manage, deploy, or interact with any Azure resource — even if they don't explicitly mention "az cli". Also trigger when the user asks about Azure CLI commands, syntax, or wants to…
context-forge
Use when starting a brand-new project that needs AI-agent context (CLAUDE.md, AGENTS.md, skills, rules, MCP, spec workflow) set up from day one. Discusses goals → matches catalog know-how → creates a new GitHub repo with everything wired in. Keywords: harness engineering, bootstrap project, context engineering…
unity-agent-workflows
Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…