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/techtalk/ai-readiness-assessment/agents-mdgit clone --depth 1 https://github.com/techtalk/ai-readiness-assessmentWrote 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/techtalk/ai-readiness-assessment/agents-md)<a href="https://agentmods.dev/instructions/techtalk/ai-readiness-assessment/agents-md"><img src="https://agentmods.dev/badge/instructions/techtalk/ai-readiness-assessment/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 5.1 | $0.01727 | $0.01727 |
| Opus 5 | $0.00864 | $0.00864 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
ai-readiness-assessment 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 5d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Human-curated knowledge for anyone — person or agent — working on this plugin. It is the operational layer that complements two other surfaces and deliberately does not duplicate them:
HARNESS.mdholds the rules (conventions and enforced constraints). Don't restate them here.docs/explanation/holds the user-facing why (why the model, why coherence beats level, why self-contained). Link to it, don't copy it.
This file is the rest: the gotchas, the workflows, the test strategy,
and the decisions-with-rationale that neither of those captures. Humans
edit this file; agents propose changes via /reflect and a human
promotes them.
Status: DRAFT for review. Seeded from the first
REFLECTION_LOG.mdentry and the decisions made building the plugin. Edit freely — you own it.
GOTCHAS
Practical traps, with what happened and how to avoid them.
- The tests assert against committed sample assessments, not live
output.
tests/run.pyreads the pre-written reports undertests/fixtures/<level>/assessments/. A green check does not prove your instrument change is reflected — it only proves the committed samples still satisfy the structural assertions. When you change scoring, you must regenerate those samples (see TEST_STRATEGY). - Retroactive releases need real tags.
gh release create --target <short-sha>returns HTTP 422 for past commits. Push an annotated git tag first, thengh release create --verify-tag. (Tags aren't subject to branch protection.) - The two manifests must agree on the version.
plugin.jsonandmarketplace.jsonmust carry the sameversion; the release workflow and the changelog gate both fail on a mismatch. mainis branch-protected. You can't push to it directly — branch and open a PR. Two required checks must pass:A-tier structural assertionsandChangelog gate.
WORKFLOWS
Changing the instrument
The instrument is the prose in commands/ai-readiness-assess.md and
skills/ai-readiness-assessment/SKILL.md. When you change it:
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.
- 5d ago First seen · 154 lines · 1,727 tokens per session scan A 0874dbe14713
ai-readiness-assessment AGENTS.md is an instructions file published in the GitHub repository techtalk/ai-readiness-assessment (9 stars, last pushed 18d ago), licensed Apache-2.0. It adds 1,727 tokens to every session, about $0.0086 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
rust-faf-mcp AGENTS.md
AGENTS.md instructions for Wolfe-Jam/rust-faf-mcp, covering agents.md — rust-faf-mcp, agents.md — rust-faf-mcp, setup & build, run the tests and where things live.
rust-faf-mcp CLAUDE.md
Claude Code instructions for Wolfe-Jam/rust-faf-mcp, covering claude.md - rust-faf-mcp and project: rust-faf-mcp.
bun-sticky-faf CLAUDE.md
Instructions for Wolfe-Jam/bun-sticky-faf, covering claude.md — bun-sticky, what this is, stack, context and bun-sticky.
ai-literacy-superpowers AGENTS.md
AGENTS.md instructions for Habitat-Thinking/ai-literacy-superpowers, covering compound learning, style, gotchas, archdecisions and teststrategy.
ai-literacy-superpowers copilot-instructions.md
Copilot instructions for Habitat-Thinking/ai-literacy-superpowers, covering project conventions and constraints, stack, naming, file structure and error handling.
ai-literacy-superpowers CLAUDE.md
Claude Code instructions for Habitat-Thinking/ai-literacy-superpowers, covering ai-literacy-superpowers — conventions, always work on a branch, pr workflow, commit messages and changelog.