converge-to-spec

converge-to-spec is a skill for Claude Code, Codex from Tx1207/hello-scholar. It costs 28 tokens per session (386 once invoked), scanned A, original, MIT.

A review that compares a finished implementation with its written specification and plan. A Spec Bundle is the set of documents that records those requirements and tasks.

In plain words
What is it for?
Use it to check a completed project against its specification and plan, or to save the audit findings as follow-up tasks.
Why use it?
It identifies where the implementation has not followed the agreed contract before any repair work begins.

Skill for Claude CodeCodex

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

Good fit Use it to check a completed project against its specification and plan, or to save the audit findings as follow-up tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tx1207/hello-scholar/converge-to-spec
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 Tx1207/hello-scholar --skill converge-to-spec
Clone the repo
git clone --depth 1 https://github.com/Tx1207/hello-scholar

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 converge-to-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/tx1207/hello-scholar/converge-to-spec/github.svg)](https://agentmods.dev/skills/tx1207/hello-scholar/converge-to-spec)
Your own site
<a href="https://agentmods.dev/skills/tx1207/hello-scholar/converge-to-spec"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/converge-to-spec/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 converge-to-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/tx1207/hello-scholar/converge-to-spec"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/converge-to-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 386 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 $0.00028 $0.00386
Opus 5 $0.00014 $0.00193
Sonnet 5 $0.00006 $0.00077
Haiku 4.5 $0.00003 $0.00039

Measured 2d ago against content hash 9cc1e691c19b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

converge-to-spec 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 2d 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/converge-to-spec/SKILL.md · 30 lines

What it actually says

Converge to Spec

Compare the real implementation with the selected Spec, including a draft or partially implemented Spec. An audit is read-only regardless of progress; if the user asks to audit and fix, identify the gaps, then continue with in-scope repairs and verification under the same authorization.

Establish the comparison

Identify the exact Spec path, revision, status, target code or worktree state, and initial Git changes. Read the Spec, relevant Architecture, code, tests, configuration, and linked experiment Records. Use historical Plan/Tasks only when explicitly auditing an unmigrated legacy bundle, and state that boundary; they do not control current execution.

Run hello-scholar docs check when available. A draft status, partial implementation, or failing check is evidence to report, not a reason to refuse the comparison.

Audit acceptance

For every material AC-NN, record:

  • the requirement and current conclusion: satisfied, partial, missing, contradictory, or not verifiable;
  • severity and user impact;
  • direct evidence with paths, lines, commands, results, or a linked Record;
  • the smallest credible repair or verification direction.

Also identify unrequested interfaces, dependencies, compatibility layers, duplicate owners, or stale behavior within the Spec's boundary. Tests passing do not prove an AC they do not cover, and old summaries do not replace current evidence. Do not invent logs when no executable verification exists; use code evidence and state its limit.

Return the result

Lead with material findings, then summarize satisfied acceptance and the exact fresh commands still needed. Name the compared Spec revision and working-tree state so the result can be interpreted later. Do not modify source, tests, Specs, Records, Architecture, or Indexes during the audit.

Files

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.

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. 2d ago Changed · -53 lines · -19 tokens per session 9cc1e691c19b
  2. 11d ago First seen · 83 lines · 47 tokens per session scan A c1e455b5dd27

Subscribe to this mod's changes

converge-to-spec is a skill published in the GitHub repository Tx1207/hello-scholar (6 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 386 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 2026-08-31.