agora: Skill for Claude Code

.claude/skills/instrument-control/SKILL.md

instrument-control is a skill for Claude Code from DanceNitra/agora. It costs 111 tokens per session (1,265 once invoked), scanned A, original, MIT.

A checking procedure for findings made with research or analysis tools. It treats a reported zero, missing item, error, or count as possibly caused by the tool itself until a comparison check confirms it.

In plain words
What is it for?
Use it before reporting absences, 404 errors, empty results, counts, percentages, or pass/fail decisions. It guides you to test the same method against something known to be present.
Why use it?
It helps prevent broken searches, blocked links, or incomplete data from being mistaken for facts about the real world. This is especially useful when reporting negative findings or measurements.

Skill for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths.

This is DanceNitra/agora's own configuration. It tells Claude Code how to work on agora itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agora configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DanceNitra/agora. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DanceNitra/agora/main/.claude/skills/instrument-control/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DanceNitra/agora

Made for: Claude Code.

Wrote 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.

agentmods badge for instrument-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/dancenitra/agora/instrument-control.svg)](https://agentmods.dev/skills/dancenitra/agora/instrument-control)
Your own site
<a href="https://agentmods.dev/skills/dancenitra/agora/instrument-control"><img src="https://agentmods.dev/badge/skills/dancenitra/agora/instrument-control.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,265 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.01265
Opus 5 $0.00056 $0.00633
Sonnet 5 $0.00022 $0.00253
Haiku 4.5 $0.00011 $0.00127

Measured 7d ago against content hash 1745b95c44f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

instrument-control scanned grade A with 1 finding 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 7d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

remembered: an empty grep/find, a `| head` truncated search, a `github.com/blob` curl, a `gh issue/pr`
.claude/skills/instrument-control/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instrument control — the finding is about your tool until a control says otherwise

Why this exists

2026-08-17: twelve instrument failures in one day. Not twelve mistakes of care — twelve findings that were true of the measuring apparatus and false of the world. Every single one was caught by a LATER measurement, never by confidence, and the most expensive one was one sentence away from persuading the owner to dismantle his own frontier lock.

That is the whole argument. You cannot feel the difference between a real zero and a broken instrument. You can only measure it.

The one rule

A negative, an absence, or a count does not leave the workspace without a control that would have failed.

Everything below is that rule, specialised.

The six shapes, each from a real 2026-08-17 failure

shape what happened the control
Absence by uncontrolled instrument Two published receipt links reported dead on a 404. The control — the same fetch against a file known to be present — also 404'd. GitHub throttles unauthenticated blob URLs; the links were fine. Run the identical query against something you KNOW is there. If the control fails, the finding is void.
Wrong field / wrong path A bucket scored "0 of 3 on-priority" because the probe read question while the code builds its quest from origin. Another missed a kind == "research" filter the code applies. Read the CONSUMING code and measure the field it reads, not the one that looks right.
Truncated window grep -n "^import re" file | head -8 declared the import missing. It sits at line 466. Count before you conclude (grep -c), or drop the pipe. A window that can hide the hit is not a search.
The harness creates the state it reports A probe passed receipts=True and then reported "receipts enabled, chain empty". Same file, three ways of opening it, three verdicts. Vary the instrument. Open it three ways; if the finding moves, it is about the setup.
A handler swallowing the defect A thread checker returned UNKNOWN for everything because json was not imported and the NameError landed in its own except. It reported "0 not open" and looked clean. A control must distinguish failed to look from looked and found nothing. Never let an unknown render as a pass.
Comparing values that carry noise Two pytest runs with identical outcomes compared unequal, because the summary string ends in the elapsed time — so a SURVIVING mutant was reported as killed. Compare the extracted numbers, never the rendered line.

Read the full file on GitHub · 77 lines

Changes

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.

  1. 7d ago First seen · 77 lines · 111 tokens per session scan A 1745b95c44f7

Subscribe to this mod's changes

instrument-control is a skill published in the GitHub repository DanceNitra/agora (3 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 1,265 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

Evaluation

Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.

agentic-in/elephant-agent · 25 tokens

create-custom-grader

Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.

NVIDIA/SkillEvaluator · 35 tokens

ceo-setup

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 60 tokens

developer-setup

One-time onboarding for the developer workflow — installs github-workflow missions, creates the commitments workspace, registers per-repo projects, writes calibration memories. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 49 tokens

api-caller

Call any REST API dynamically. Make GET, POST, PUT, DELETE requests to any endpoint with custom headers and JSON body.

NVIDIA/SkillEvaluator · 29 tokens

commitment-setup

One-time setup for the commitments tracking system. Creates workspace structure, schema docs, and installs triage and digest missions. Excluded from activation once projects/commitments/README.md exists in the workspace (the file this skill writes as its first step).

suyoumo/ClawProBench · 58 tokens