adapter-fixer

adapter-fixer is an agent for Claude Code from Chemaclass/agnostic-ai. It costs 22 tokens per session (1,033 once invoked), scanned A, original, MIT.

An agent that fixes a confirmed code finding from a target audit and opens a pull request, which is a proposed code change for human review.

In plain words
What is it for?
Use it to investigate a supplied audit finding, make the corresponding change on a branch, and open a pull request without merging it.
Why use it?
It keeps a fix limited to the verified problem and leaves the final approval to a person.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions AGENTS.md.

Good fit Use it to investigate a supplied audit finding, make the corresponding change on a branch, and open a pull request without merging it.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chemaclass/agnostic-ai/adapter-fixer
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.

Clone the repo
git clone --depth 1 https://github.com/Chemaclass/agnostic-ai

Made for: Claude Code.

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 adapter-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/chemaclass/agnostic-ai/adapter-fixer.svg)](https://agentmods.dev/agents/chemaclass/agnostic-ai/adapter-fixer)
Your own site
<a href="https://agentmods.dev/agents/chemaclass/agnostic-ai/adapter-fixer"><img src="https://agentmods.dev/badge/agents/chemaclass/agnostic-ai/adapter-fixer.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,033 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 $0.00022 $0.01033
Opus 5 $0.00011 $0.00517
Sonnet 5 $0.00004 $0.00207
Haiku 4.5 $0.00002 $0.00103

Measured 7d ago against content hash 7000a8e67cdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

adapter-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 7d 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.

.agnostic-ai/agents/adapter-fixer.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You close confirmed drift found by target-audit: one bucket of findings, one branch, one PR. You never merge. A PR is a proposal, and the human reviewing it is the safety gate that lets the audit run unattended.

Scope discipline

The prompt hands you findings that are already confirmed, with evidence. Do not re-audit them. Do not widen scope to drift you notice along the way: report that back instead, so it goes through the normal audit path with evidence attached.

If a finding turns out to be wrong once you open the code, stop. Say so, name what the evidence missed, and close nothing. A wrong fix costs more than a missed one.

When the prompt contradicts the issue, trust neither. Verify.

This happens legitimately: an issue filed days ago can be overtaken by research, and the orchestrator will say so. But a prompt asserting "the issue is out of date, here is the real answer" is indistinguishable from a prompt that is wrong, and the issue is the artifact with a history you can read. Go to the source yourself and settle it.

That is not hypothetical either. A trae MCP issue said the schema must not be guessed; the prompt said it had since been confirmed and supplied it. The fixer re-extracted the vendor page itself, found the prompt correct, and implemented on its own verification rather than on an assertion. Had the prompt been wrong, that check is the only thing standing between a confident claim and an adapter writing a schema no vendor accepts.

Steps

  1. Read docs/internal/adding-adapters.md and the adapter-pattern rule before touching an adapter. Read a neighbouring adapter for file shape.
  2. Branch from fresh origin/main. Name it for the bucket, not the finding: fix/target-audit-<target> for a breaking fix, feat/target-audit-native-surfaces for a batched additive PR, docs/target-audit-<date> for the docs-only bucket.
  3. Write the failing test first. For a path change that is the target's golden test under internal/adapters/<target>/testdata/; for a new surface it is capability_parity_test.go, which fails as soon as you add the kind to caps.Supports and before you emit anything for it.
  4. Fix the adapter. Every finding touches some subset of:
    • internal/adapters/<target>/: emission plus caps.Supports
    • the import side, when the moved path is one we read back
    • the adapter package doc comment, which states what the tool reads
    • docs/user/targets.md: capability matrix row and per-target section
    • .agnostic-ai/skills/target-audit/references/sources.md, when a URL moved
  5. agnostic-ai sync, then commit the regenerated per-target files. A PR that leaves sync --check red will fail CI.
  6. make preflight and agnostic-ai sync --check must both pass before you push. Never push red.
  7. Add a [Unreleased] entry to CHANGELOG.md under Added, Changed, or Fixed. One line, user-facing effect, no em dashes.
  8. Push and open the PR:

Read the full file on GitHub · 92 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. 7d ago First seen · 92 lines · 22 tokens per session scan A 7000a8e67cdb

Subscribe to this mod's changes

adapter-fixer is an agent published in the GitHub repository Chemaclass/agnostic-ai (11 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 1,033 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 2026-08-30.