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 bahayonghang/my-ai-cli-toolkit --skill agents-md-improvergit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-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/bahayonghang/my-ai-cli-toolkit/agents-md-improver)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/agents-md-improver"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/agents-md-improver.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 | $0.00107 | $0.00692 |
| Opus 5 | $0.00053 | $0.00346 |
| Sonnet 5 | $0.00021 | $0.00138 |
| Haiku 4.5 | $0.00011 | $0.00069 |
Grade A, and why
agents-md-improver 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 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.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md Improver
Produce lean repository guidance grounded in the Codex instruction chain that applies to the launch context.
Action Boundary
- Audit/optimize/plan: inspect and return an evidence-first report with proposed diffs; do not write.
- Approved plan or explicit scoped change/fix: edit local in-scope files and validate without another approval round.
- Fully specified trivial edit: implicit routing stays with direct editing; explicit skill invocation uses a minimal check, edit, validation, then stops.
- Confirm user-global, external, destructive, costly, or scope-expanding work. Never write Codex-home guidance unless requested.
Workflow
- Resolve project root, launch CWD, candidates, and effective config evidence.
Read Codex discovery semantics before
declaring files active. Prefer structured tools; use one-line
rg --files --hiddenwith include/exclude globs as the shell fallback. - Build the root-to-CWD chain, shadows, empty-file and byte-budget state.
Inventory off-chain files separately; unavailable config is
missing evidence. - Verify commands, paths, ownership, boundaries, and recurring failures. Apply quality criteria; decide durable instruction need independently from navigation need.
- Use the report contract for audits. For edits, follow update guidelines and evidence-backed templates.
- Run the smallest checks proving the changed claims, then stop.
Evidence Rules
- Separate facts, defaults, inference, and missing evidence; retry suspiciously empty reads once or twice.
- Treat
evals/as release evidence, not model or human proof. - Preserve human/managed content. Change both sibling fenced
code_map.mdtemplates only when their shared contract changes. - Audit existing overrides; create one only for an explicit temporary or strong override need.
What ships with it
22 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.
- agents/interface.yaml 826 B
- evals/evals.json 5.9 KB
- evals/output/cases.jsonl 8.3 KB
- evals/output/fixtures/agents-md-scenarios.md 3.9 KB
- manifest.json 1.4 KB
- references/codex-agents-discovery.md 3.7 KB
- references/quality-criteria.md 3.1 KB
- references/report-format.md 2.6 KB
- references/templates.md 4.4 KB
- references/update-guidelines.md 3.4 KB
- reports/artifact-design-profile.json 4.4 KB
- reports/artifact-design-profile.md 4.1 KB
- reports/output_blind_answer_key.json 1.5 KB
- reports/output_blind_review_pack.json 8.6 KB
- reports/output_blind_review_pack.md 4.7 KB
- reports/output_quality_scorecard.json 22 KB
- reports/output_quality_scorecard.md 1.6 KB
- reports/output-risk-profile.json 6.5 KB
- reports/output-risk-profile.md 2.9 KB
- reports/prompt-quality-profile.json 5.3 KB
- reports/prompt-quality-profile.md 4.5 KB
- tests/contracts.test.mjs 7.9 KB runs code
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.
- 7d ago First seen · 66 lines · 107 tokens per session scan A 0989cd587ee1
agents-md-improver is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 692 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
talk-like-scarletkc
A writing guide that makes text sound like the developer scarletkc, including posts, comments, technical opinions, project documents, and translations.
marketing-copy
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls to action, press-style announcements, and the naming of a product for another language or market. Covers what may be…
scoped-change
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it. Use when scope is ambiguous, a diff touches neighboring surfaces, required dependent edits are unclear, or a proposed compatibility layer, migration, fallback, flag…
codex-cli
When handing work to the Codex CLI earns its cost, and how to size the run: second-model review, bounded implementation hand-offs, sandbox permissions, model and reasoning effort. Use when the user asks for Codex or codex exec, when a change is complex or high-stakes enough that an independent reviewer would change…
aerospace-engineering-technician
Use when a task needs the judgment of an Aerospace Engineering and Operations Technologist/Technician — verifying an installed fastener's preload against a drawing's torque callout via the T=K·D·F relationship, reducing strain-gauge data from a structural proof-load test into stress and checking it against an…
agricultural-sciences-professor
Use when a task needs the judgment of a tenure-track or tenured Agricultural Sciences faculty member at a land-grant university — deciding whether to submit a grant this cycle versus wait, allocating time across the teaching/research/extension appointment split, diagnosing a stalled graduate student or field trial, or…