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 eugenelim/agent-ready-repo --skill contract-acquisitiongit clone --depth 1 https://github.com/eugenelim/agent-ready-repoWrote 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/eugenelim/agent-ready-repo/contract-acquisition)<a href="https://agentmods.dev/skills/eugenelim/agent-ready-repo/contract-acquisition"><img src="https://agentmods.dev/badge/skills/eugenelim/agent-ready-repo/contract-acquisition/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/eugenelim/agent-ready-repo/contract-acquisition"><img src="https://agentmods.dev/badge/skills/eugenelim/agent-ready-repo/contract-acquisition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 57 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Memory Poisoning · line 158 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00218 | $0.05055 |
| Opus 5 | $0.00109 | $0.02527 |
| Sonnet 5 | $0.00044 | $0.01011 |
| Haiku 4.5 | $0.00022 | $0.00505 |
Grade A, and why
contract-acquisition 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 11d 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.
| **weak / none — infra** | bespoke REST + `curl`, hand-rolled bare-metal provisioning, an undocumented internal API | no trustworthy static oracle | **declare weak; shift weight to the runtime probe** — do not invent st How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: contract-acquisition
This skill answers one question before you author anything against a platform or library you don't know cold: what is its real contract — the flag set, resource schema, naming and immutability rules, and packaging model of a platform; the versioned signatures, deprecations, and call-order / lifecycle constraints of a library — and where does that contract come from? The field-report failures this closes were not reasoning failures; they were contract failures: invented CLI flags, a violated naming regex, a wrong tool-schema shape, an immutable-field collision, a managed-runtime import model guessed wrong — and, on the software side, a non-existent signature, a removed keyword argument, a wrong return type, a call against a deprecated API. The fix is not to memorize more clouds or more libraries. It is to drive the toolchain's own deterministic oracles — the validate / plan / schema tools a stack ships, the type checker / compiler / introspection a language ships — and to ground authoring in what they return, declaring honestly how strong that oracle is.
This is the generalization of AGENTS.md's "Grep to verify a function exists before importing it": don't guess a flag, a schema field, a constraint, a signature, or a packaging assumption when the toolchain can tell you the truth deterministically. The bare grep confirms a symbol exists; this skill confirms its contract.
The four-way carve — who owns which infra question. Four distinct questions, four owners; keep the lines clean both ways.
contract-acquisition(this skill) — is the IaC / invocation correct against the platform's structural contract? (Does this flag exist, this field accept this value, this resource name match the regex, this property is immutable?)cloud-implementation-craft(anoperational-safetymodule) — will the call path even succeed? under-permissioning, timing / eventual-consistency, retry / cold-start, dependency ordering, packaging.security-checklists— is this too open? over-permissioning and security config (IAM blast radius, public exposure, secrets in state).- the policy-as-code / CSPM scanner — is the config against policy? per-provider secure-config baselines from vendor-maintained rulesets.
A leaked credential is
security-checklists; an under-scoped role that makes the call fail iscloud-implementation-craft; a non-existent flag or an immutable-field collision is this skill.The four owners above are the infra-question owners. The software surface — an unfamiliar framework / library's contract (signatures, deprecations, call-order / lifecycle) — also rides this skill, across the same tiered protocol (T0 version → T1 type-checker / introspection oracle → T2 curated skill → T3 versioned docs → runtime probe), not just one tier.
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.
- 11d ago First seen · 305 lines · 218 tokens per session scan A 7b6b8f481442
contract-acquisition is a skill published in the GitHub repository eugenelim/agent-ready-repo (21 stars, last pushed today), licensed Apache-2.0. It adds 218 tokens to every session and 5,055 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
supervisor
Autonomous multi-agent quality supervisor and release gate. Use when a user wants the best possible result, asks for rigorous review, or when a substantive answer/deliverable should be challenged before release. Decomposes the task, fans out independent subagents, uses specialist and adversarial judges, verifies…
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
hns-workflow-ci-loop
Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see…
moai-harness-learner
Harness learning subsystem coordinator. Produces Tier 4 auto-update proposal payloads consumed by the orchestrator (which surfaces them via AskUserQuestion) and orchestrates Apply/Rollback flows. Triggers when harness learning proposals are pending or learning lifecycle management is needed.
moai-platform-chrome-extension
Chrome Extension Manifest V3 development specialist covering service workers, content scripts, message passing, chrome. APIs, side panel, declarativeNetRequest, and Chrome Web Store publishing. Use when building browser extensions.
moai-domain-humanize
AI text humanization and 윤문 (post-editing) specialist that detects and removes AI tells while preserving meaning, facts, and figures. Covers Korean, English, Japanese, and Chinese with a shared severity model (S1/S2/S3), quality grades (A/B/C/D), and 30%/50% over-editing guardrails. Use to make AI-generated text read…