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 charlieviettq/awesome-agent-skill --skill grad-antgit clone --depth 1 https://github.com/charlieviettq/awesome-agent-skillWrote 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/charlieviettq/awesome-agent-skill/grad-ant)<a href="https://agentmods.dev/skills/charlieviettq/awesome-agent-skill/grad-ant"><img src="https://agentmods.dev/badge/skills/charlieviettq/awesome-agent-skill/grad-ant/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/charlieviettq/awesome-agent-skill/grad-ant"><img src="https://agentmods.dev/badge/skills/charlieviettq/awesome-agent-skill/grad-ant.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 | $0.00112 | $0.01073 |
| Opus 5 | $0.00056 | $0.00536 |
| Sonnet 5 | $0.00022 | $0.00215 |
| Haiku 4.5 | $0.00011 | $0.00107 |
Grade A, and why
"grad-ant" 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 9d 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.
This is a copy
98% identical to grad-ant — 8 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Actor-Network Theory (ANT)
Overview
Actor-Network Theory treats human and non-human entities symmetrically as "actants" that form networks through processes of translation. Developed by Latour, Callon, and Law, ANT traces how heterogeneous networks are assembled, stabilized, and sometimes dissolved — rejecting the a priori distinction between the social and the technical.
When to Use
- Mapping how a technology, innovation, or practice became accepted (or failed)
- Analyzing the role of artifacts, standards, or devices in stabilizing social arrangements
- Tracing controversy and network-building in science and technology
- Understanding why a seemingly good innovation failed to gain adoption
When NOT to Use
- When the analysis requires strong normative judgments (ANT is descriptive, not prescriptive)
- When macro-level structural explanations are needed (ANT resists pre-given social categories)
- When non-human agency is irrelevant to the research question
Assumptions
IRON LAW: Non-human actors have AGENCY in ANT — treating technology
as a passive tool violates the framework's core principle. If your
analysis strips agency from artifacts, you are NOT doing ANT.
Key assumptions:
- Generalized symmetry — human and non-human actors are described in the same analytical terms
- No a priori distinctions between the social, technical, and natural
- Networks are the unit of analysis, not individuals or structures
- Stability is an achievement, not a given — networks require continuous maintenance
Methodology
Step 1: Identify the Controversy or Innovation
Select the phenomenon to trace. Follow the actors — do not impose pre-existing categories.
Step 2: Map the Actants
List all relevant human and non-human actors (people, organizations, technologies, documents, standards, natural entities) involved in the network.
Step 3: Trace the Four Moments of Translation (Callon, 1986)
| Moment | Description |
|---|---|
| Problematization | A focal actor defines the problem and positions itself as an obligatory passage point |
| Interessement | Devices and strategies lock other actors into proposed roles |
| Enrollment | Actors accept and perform their assigned roles in the network |
| Mobilization | Enrolled actors come to represent wider constituencies; the network stabilizes |
What ships with it
1 file 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.
- 9d ago First seen · 107 lines · 112 tokens per session scan A 1c6d5b39f2d3
"grad-ant" is a skill published in the GitHub repository charlieviettq/awesome-agent-skill (26 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 1,073 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to grad-ant, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
energy-simulation
Building energy simulation and analysis for construction. Calculate heating/cooling loads, evaluate envelope performance, optimize HVAC sizing, and ensure energy code compliance.
co2-carbon-footprint
Calculate CO2 emissions and carbon footprint from BIM model data. Analyze embodied carbon by material, element, and building system.
cwicr-unit-converter
Convert between construction measurement units. Handle metric/imperial conversion, area/volume calculations, and unit normalization for CWICR data.
cwicr-waste-calculator
Calculate material waste factors and losses using CWICR norms. Apply waste percentages, cutting losses, and spillage factors to material quantities.
carbon-calculator
Calculate embodied carbon in construction materials. Track CO2 emissions, compare alternatives, and generate sustainability reports.
co2-estimation
Calculate carbon footprint of construction projects. Estimate CO2 emissions from materials, transportation, and construction processes using emission factors databases.