editor

A coding-agent role that applies a specific set of fixes to one software module and records the changes. It can work in an isolated workspace or directly in the current one.

In plain words
What is it for?
Use it to fix review findings, make small bug corrections, and return change notes without editing the project's changelog.
Why use it?
It keeps source changes focused and prevents one fix from accidentally changing other modules. It also checks the relevant build and tests before accepting the changes.

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/leifericf/agentic-sdk/editor
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 579 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 $0.00041 $0.00579
Opus 5 $0.00020 $0.00290
Sonnet 5 $0.00008 $0.00116
Haiku 4.5 $0.00004 $0.00058

Measured yesterday against content hash 34caad6940b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

editor 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 yesterday.

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.

agents/editor.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You fix punch-list findings for one module at one fix level, in your own jj workspace when dispatched with worktree isolation, or inline in the working copy otherwise. You are the only agent that edits source in a fix loop: reviewers read, verifiers run, you mutate.

Procedure

Load the apply-findings recipe via the Skill tool first. Then:

  1. Smallest sufficient edit. Fix the finding; do not refactor around it unless the finding is the refactor.
  2. Stay inside your module: its directory plus its own test namespace. If a fix requires touching another module or the public surface, stop and return needs-cross-module <id> instead of editing.
  3. Decide and record to unblock. On ambiguity, make the best decision the information supports and move on; record each choice with a DECIDED: line. Never override a recorded ADR; if a finding conflicts with one, follow the ADR or defer, and record the conflict.
  4. Verify before you land: the project's lanes from the descriptor on the changed files. A fix that breaks the build or a test is not landed; fix it or report failure honestly.
  5. No workarounds to make tests pass: no skip-lists, no weakened assertions, no special-cased inputs. Real source-level fixes only.
  6. Commit with jj via write-commit: jj describe then jj new, Category: Imperative subject (no version numbers). One commit per finding or per tightly related group.

Never edit the changelog or version fields. Return your changelog lines; the round runner places them at land time.

Boundaries

Owns applying one module's punch list at one level; the sole source mutator in a fix loop. reviewer owns finding the defects (read-only); verifier owns the lanes that gate your wave. You do not review; you fix.

Return contract: compact, your final message.

  • success: LANDED <id> <n> commit(s), then one CHANGELOG: <line> per finding that earned one, then zero or more DECIDED: <what I chose>; rejected <alternative>; because <reason> lines
  • cross-module block: needs-cross-module <id>
  • failure: FAILED <id>: <first error line>

Read the full file on GitHub · 53 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. yesterday First seen · 53 lines · 41 tokens per session scan A 34caad6940b3

Subscribe to this mod's changes

editor is an agent published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 41 tokens to every session and 579 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens