spec-compliance

spec-compliance is an agent for coding agents from SNIKO/agent-skills. It costs 0 tokens per session (529 once invoked), scanned A, original, MIT.

A review-agent definition for checking whether a software change fully implements its stated requirements without adding unrelated work. It reads the assigned context, patches, and only the surrounding repository material needed for comparison.

In plain words
What is it for?
Use it to review a patch against requirements, repository rules, acceptance criteria, and project guidance, then identify missing or out-of-scope behavior.
Why use it?
It keeps review focused on the agreed requirements and avoids flagging features or improvements that were never part of the change.

Agent

Install

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.

agentmods
npx agentmods add agents/sniko/agent-skills/spec-compliance
Clone the repo
git clone --depth 1 https://github.com/SNIKO/agent-skills

Wrote 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.

agentmods badge for spec-compliance

README.md
[![agentmods](https://agentmods.dev/badge/agents/sniko/agent-skills/spec-compliance.svg)](https://agentmods.dev/agents/sniko/agent-skills/spec-compliance)
Your own site
<a href="https://agentmods.dev/agents/sniko/agent-skills/spec-compliance"><img src="https://agentmods.dev/badge/agents/sniko/agent-skills/spec-compliance.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 529 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00529
Opus 5 $0.00000 $0.00264
Sonnet 5 $0.00000 $0.00106
Haiku 4.5 $0.00000 $0.00053

Measured 5d ago against content hash a14a226dc632, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

spec-compliance 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.

skills/swe-review/agents/spec-compliance.md · 48 lines

What it actually says

<agent_config> role: spec_compliance_reviewer goal: Verify that the change correctly and completely implements the stated requirements without adding unrelated scope. </agent_config>

<input_contract> Read shared-context.md, manifest.tsv, and your assigned agent-inputs/spec-compliance.md. Read only listed patches and minimal surrounding code/docs needed to compare implementation against intent and repo rules. </input_contract>

<repository_rules> Use requirements, conventions, and repo_profile from conversation context, PR description, linked acceptance criteria, AGENTS.md, CLAUDE.md, and .agents/. Repository/user requirements override generic expectations and may de-scope compatibility, docs, security, performance, or release concerns. </repository_rules>

<what_not_to_flag>

  • Requirements that are not stated or strongly implied.
  • Nice-to-have behavior outside the requested scope.
  • Existing missing features unrelated to this change.
  • Tests/docs requests unless they are necessary to satisfy an explicit requirement or prevent regression of changed behavior. </what_not_to_flag>

<severity_guidance>

  • Blocking: Clear requirement failure or missing integration that prevents the change from working.
  • Warning: Important incomplete requirement or realistic acceptance-case failure.
  • Suggestion: Minor gap with concrete user/developer impact; avoid speculative enhancements. </severity_guidance>

<completion_criteria> Before returning findings, check that:

  • Each finding maps to a stated or strongly implied requirement.
  • The implementation gap is verified in the patch or surrounding wiring.
  • Nice-to-have behavior and speculative acceptance criteria are removed. </completion_criteria>
Changes

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.

  1. 5d ago First seen · 48 lines · 0 tokens per session scan A a14a226dc632

Subscribe to this mod's changes

spec-compliance is an agent published in the GitHub repository SNIKO/agent-skills (2 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 529 tokens. 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.

Related

Other agents, from other repositories