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 youdotcom-oss/dx-toolkit --skill optimize-agents-mdgit clone --depth 1 https://github.com/youdotcom-oss/dx-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/skills/youdotcom-oss/dx-toolkit/optimize-agents-md)<a href="https://agentmods.dev/skills/youdotcom-oss/dx-toolkit/optimize-agents-md"><img src="https://agentmods.dev/badge/skills/youdotcom-oss/dx-toolkit/optimize-agents-md/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/youdotcom-oss/dx-toolkit/optimize-agents-md"><img src="https://agentmods.dev/badge/skills/youdotcom-oss/dx-toolkit/optimize-agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.00850 |
| Opus 5.5 | $0.00015 | $0.00340 |
| Sonnet 5.5 | $0.00008 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
optimize-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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize AGENTS.md
Purpose
Improve AGENTS.md and scoped agent instruction files without weakening the
repo's operational contract.
Use this skill when the user asks to:
- reduce instruction bloat
- clarify confusing workflow rules
- add a lesson learned from a recent mistake
- remove stale or duplicate guidance
- reorganize agent instructions for better retrieval
- update commit, PR, validation, skill, or evidence-collection rules
Do not optimize by chasing a fixed token target. Preserve rules that encode repo-specific safety, validation, or workflow constraints even when they are verbose.
Authority
Before editing instructions, collect current evidence:
git log --oneline -20
git diff main...HEAD --stat
git log --oneline -- AGENTS.md
find .agents/skills -name 'SKILL.md' | sort
When sources conflict, use the repo hierarchy:
src/code and executable behavior- git history
AGENTS.mdby scope- docs and skills
Update stale prose rather than making code conform to stale docs.
Editing Rules
- Keep concrete rules that prevent real failures, even if they cost tokens.
- Prefer one precise rule over several overlapping reminders.
- Preserve current repo conventions: Bun-first workflow,
ghfor GitHub, conventional commits, scoped validation, directory boundaries, module naming, and skill-trigger guidance. - Remove references to retired surfaces only after verifying with
rg. - Do not introduce a public validation CLI unless it exists in the repo.
- Do not replace operational rules with generic advice agents already know.
- Do not add broad "always run everything" gates when AGENTS.md already requires area-aware validation.
Workflow
-
Identify the target scope:
- root
AGENTS.md - nested
AGENTS.md - skill-local instructions
- all of the above
- root
-
Search before changing:
rg -n "stale-term|removed-command|old-path" AGENTS.md docs skills src package.json
git log --oneline -- AGENTS.md
- Classify each candidate edit:
remove: stale, duplicated, or generic instructionmerge: repeated project-specific ruleclarify: correct rule that caused confusionadd: recent failure mode or missing project constraint
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.
- 1mo ago First seen · 135 lines · 38 tokens per session scan A d51d14b71955
optimize-agents-md is a skill published in the GitHub repository youdotcom-oss/dx-toolkit (25 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 850 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
opik-test
Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the trace's input and one or two binary assertions — so a fix can be verified by the compare skill. Works over the SDK; uses the MCP write tool when connected. Returns the suite, the item, and the assertion.…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
quantum-fermi-hubbard-vqe
A variational quantum simulation of the open-boundary Fermi–Hubbard chain, a model of particles hopping between sites and interacting when they occupy the same system. It maps the model to qubits with the Jordan–Wigner transformation and searches for a low-energy state.
quantum-grover
A Qiskit implementation of Grover's algorithm, a quantum search method that increases the chance of finding a marked item. It can explain the method, build an explicit quantum circuit, or run it with chosen inputs.