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.
npx agentmods add agents/leifericf/agentic-sdk/editorgit clone --depth 1 https://github.com/leifericf/agentic-sdkWhat 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.
| Model | Per session | Once 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 |
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.
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:
- Smallest sufficient edit. Fix the finding; do not refactor around it unless the finding is the refactor.
- 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. - 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. - 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.
- No workarounds to make tests pass: no skip-lists, no weakened assertions, no special-cased inputs. Real source-level fixes only.
- Commit with jj via
write-commit:jj describethenjj 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 oneCHANGELOG: <line>per finding that earned one, then zero or moreDECIDED: <what I chose>; rejected <alternative>; because <reason>lines - cross-module block:
needs-cross-module <id> - failure:
FAILED <id>: <first error line>
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.
- yesterday First seen · 53 lines · 41 tokens per session scan A 34caad6940b3
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.