verify-interpreter

verify-interpreter is a skill for Claude Code, Codex from 45ck/skill-harness. It costs 25 tokens per session (941 once invoked), scanned A, original, MIT.

A guide for interpreting the statuses produced by specgraph verification. It explains whether evidence is complete, weak, missing, skipped, or covered by a waiver.

In plain words
What is it for?
Use it to understand PASS, WARN, FAIL, INSUFFICIENT, SKIP, and WAIVED results and choose the next evidence-strengthening step.
Why use it?
It turns verification output into plain-language decisions about what needs attention and what can be left alone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to understand PASS, WARN, FAIL, INSUFFICIENT, SKIP, and WAIVED results and choose the next evidence-strengthening step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/45ck/skill-harness/verify-interpreter
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.

Any agent
npx skills add 45ck/skill-harness --skill verify-interpreter
Clone the repo
git clone --depth 1 https://github.com/45ck/skill-harness

Made for: Claude Code, Codex.

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 verify-interpreter

README.md
[![agentmods](https://agentmods.dev/badge/skills/45ck/skill-harness/verify-interpreter/github.svg)](https://agentmods.dev/skills/45ck/skill-harness/verify-interpreter)
Your own site
<a href="https://agentmods.dev/skills/45ck/skill-harness/verify-interpreter"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/verify-interpreter/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.

agentmods 80×15 button for verify-interpreter

Your own site · 80×15
<a href="https://agentmods.dev/skills/45ck/skill-harness/verify-interpreter"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/verify-interpreter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 941 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00025 $0.00941
Opus 5 $0.00013 $0.00470
Sonnet 5 $0.00005 $0.00188
Haiku 4.5 $0.00003 $0.00094

Measured 6d ago against content hash fe07c46488fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify-interpreter 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 6d 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.

packs/specgraph-skills/skills/verify-interpreter/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read and explain the output of specgraph verify in plain language, then recommend next steps.

Status meanings

Status Meaning Action
PASS All required evidence thresholds met Nothing required
WARN Evidence exists but below required strength for this state Strengthen evidence or lower requirement
FAIL No evidence found for a required dimension Add evidence or add waiver
INSUFFICIENT Evidence found but strength is below required level Raise evidence strength (e.g. E0 → E2)
SKIP Spec has no evidence requirements (draft/deprecated) Review if state is correct
WAIVED Requirement waived — check expiry Verify waiver is still valid

Example output

  PASS          FEAT-001  [accepted]
  WARN          FEAT-002  [in_progress]
                 warn: No verification claims found (advisory)
  FAIL          FEAT-003  [accepted]
                 fail: No implementation claims found. Required: E2 (indexed)
  INSUFFICIENT  FEAT-004  [accepted]
                 insufficient-evidence: implementation: found E0 but required E2

Verify commands reference

specgraph verify                         # summary table for all specs
specgraph verify --spec FEAT-001         # single spec only
specgraph verify --json                  # machine-readable output
specgraph verify --changed src/foo.ts    # incremental scan (changed files only)
specgraph verify --no-db                 # dry run — skip writing to DB
specgraph explain <SPEC-ID>              # full claim breakdown for one spec
specgraph explain                        # all specs
specgraph find --spec FEAT-001           # locate files that reference a spec
specgraph find --relation IMPLEMENTS     # all IMPLEMENTS claims
specgraph find --provider annotation     # claims from a specific provider
specgraph find --strength 1              # E1 and above
specgraph waivers                        # list active waivers
specgraph waivers FEAT-001               # waivers for one spec
specgraph subject issue:beads:bd-a1b2    # show a specific Beads issue's claims
specgraph subject symbol:annotation:MyClass  # show a symbol's claims

Read the full file on GitHub · 79 lines

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. 6d ago First seen · 79 lines · 25 tokens per session scan A fe07c46488fa

Subscribe to this mod's changes

verify-interpreter is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 941 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

do-it-verify

Use when selecting evidence for a delivery claim, regression fix, installation, or branch closeout.

tdwhere123/do-it · 24 tokens

typescript-sdk

Implement or modify TypeScript SDK behavior in @composio/core or shared TypeScript packages, including tools, toolkits, sessions, auth configs, connected accounts, modifiers, and generated SDK surfaces. Use for TS runtime/API work; pair with typescript-testing for verification and cross-sdk-parity when Python must…

ComposioHQ/composio · 67 tokens

bug-fixing

Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.

ComposioHQ/composio · 63 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens

python-providers

Create, modify, test, or package Python provider adapters under python/providers, including framework-specific dependencies, public imports, type inference, and provider metadata. Use for Python provider work only; use python-sdk for core SDK changes.

ComposioHQ/composio · 49 tokens

python-sdk

Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.

ComposioHQ/composio · 60 tokens