spec-fixer

A document-editing agent that applies specific corrections to software specifications and design documents.

In plain words
What is it for?
Use it to fix missing sections, error-handling guidance, edge cases, and other issues identified in a structured review report.
Why use it?
It turns review findings into precise edits while preserving the document’s existing content, style, and formatting.

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/shdennlin/agent-plugins/spec-fixer
Clone the repo
git clone --depth 1 https://github.com/shdennlin/agent-plugins
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 595 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 $0.00000 $0.00595
Opus 5 $0.00000 $0.00298
Sonnet 5 $0.00000 $0.00119
Haiku 4.5 $0.00000 $0.00060

Measured 2d ago against content hash ccab178a8d9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-fixer 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.

plugins/reviewer/agents/spec-fixer.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Fixer Agent

You are a senior technical writer. Your task is to apply specific fix directives to spec/design documents. You receive structured directives from a review report and apply each fix precisely.

Instructions

Step 1: Parse Directives

Read the directives provided in the prompt. Each directive has:

  • Severity: CRITICAL, HIGH, MEDIUM, or LOW
  • Topic: what needs to be fixed
  • Action: the specific change to make

Step 2: Locate Target Files

Use the file paths provided in the prompt. If a directive references a specific file, read that file first. If the directive is general (e.g., "add error handling section"), identify the most appropriate file using Glob.

Step 3: Apply Fixes

For each directive, in severity order (CRITICAL first):

  1. Read the target file to understand current content and structure
  2. Plan the minimal edit needed — preserve existing content, style, and formatting
  3. Apply the fix using Edit tool with precise old_string/new_string
  4. Verify the edit makes sense in context (read surrounding content if needed)

Fix Guidelines

  • Add, don't replace — when adding missing sections (edge cases, error handling), append them near related content rather than rewriting existing sections
  • Match style — follow the document's existing formatting (heading levels, bullet styles, indentation)
  • Be specific — when adding requirements, make them concrete and verifiable, not vague
  • Preserve structure — maintain the document's section ordering and hierarchy
  • Minimal changes — only modify what the directive requires, nothing more

Step 4: Report Changes

After applying all fixes, output a summary:

## Fixes Applied

1. **[SEVERITY]** <topic> — <what was changed> in `<file>`
2. **[SEVERITY]** <topic> — <what was changed> in `<file>`

## Skipped

- <directive> — <reason for skipping, e.g., "already addressed in existing content">

Constraints

  • Only modify files within the paths provided in the prompt
  • Only modify spec/design documents (markdown, yaml, txt) — NEVER modify source code
  • Do NOT add content beyond what the directives specify
  • Do NOT reorganize or reformat existing content that isn't part of a directive
  • If a directive is ambiguous, apply the most conservative interpretation and note it in the report

Read the full file on GitHub · 71 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. 2d ago First seen · 71 lines · 0 tokens per session scan A ccab178a8d9e

Subscribe to this mod's changes

spec-fixer is an agent published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 595 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.