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 markoblogo/abvx-agent-skills --skill agent-tool-contract-reviewgit clone --depth 1 https://github.com/markoblogo/abvx-agent-skillsWrote 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/markoblogo/abvx-agent-skills/agent-tool-contract-review)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/agent-tool-contract-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/agent-tool-contract-review/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/markoblogo/abvx-agent-skills/agent-tool-contract-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/agent-tool-contract-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.00769 |
| Opus 5 | $0.00029 | $0.00385 |
| Sonnet 5 | $0.00012 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
agent-tool-contract-review 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 12d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Tool Contract Review
Use this skill to make a tool easier and safer for agents to call.
Use When
- designing or reviewing MCP tools, CLI wrappers, GitHub Actions inputs, or SET planner outputs;
- changing AGENTS.md generator templates that tell agents which commands or tools to use;
- a tool has ambiguous parameters, hidden side effects, noisy output, or weak error messages;
- agent runs repeatedly misuse a command or need human intervention after avoidable failures.
- adapting an external skill, contract, or workflow into the local skill network.
Adaptation Delta
Before writing an adapted external skill, classify each material source fragment in templates/adaptation-delta.yaml:
KEEP: retain source mechanics or schema without semantic change;ADAPT: change paths, tools, authority, terminology, or environment assumptions;ADD: introduce local guardrails, routing, verification, or project boundaries;REJECT: exclude a fragment and record the reason plus source reference.
Every entry requires a stable ID and source fragment reference. Present the complete delta to the owner before writing. Record APPROVED, REVISE, or REJECTED; silence is not approval. Preserve attribution and license constraints independently of the classification.
Review Dimensions
- purpose: what job the tool owns and what it does not own;
- schema: required fields, optional fields, enums, defaults, and validation;
- authority: read-only, proposal-only, write, destructive, external side effect;
- output: compact, structured, parseable, and stable enough for downstream agents;
- errors: actionable messages with the smallest useful recovery step;
- idempotency: safe retries, duplicate handling, and idempotency keys when needed;
- auditability: logs, dry-run mode, preview mode, and human approval boundary.
Workflow
- Identify the agent-facing tool surface and its intended caller.
- Classify the authority level:
read,plan,proposal,write, ordestructive. - Check whether the name, description, schema, and examples make the safe path obvious.
- Check whether the output can be consumed without reading a large log.
- Check error paths and retry semantics.
- Recommend the smallest contract change: rename, tighter schema, dry-run, better error, structured output, or approval gate.
What ships with it
3 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.
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.
- 12d ago First seen · 74 lines · 58 tokens per session scan A 7f0668de56f6
agent-tool-contract-review is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 769 once invoked, about $0.0003 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
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
semgrep-rule-creator
Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.