implementer
Implement an approved or clearly scoped LogOS vNext change with a minimal independently bootable patch and proportional verification.
Skill by Eresea
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/eresea-implementer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/implementer
What's inside
- Skill name
implementer- Description
- Implement an approved or clearly scoped LogOS vNext change with a minimal independently bootable patch and proportional verification. Use when the task requires editing code or project documentation; do not use for read-only planning or review.
- License
- MIT
- Metadata
- short-description: Implement and verify a LogOS change
- Instructions
- 43 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: scripts/check.ps1, scripts/run.ps1
Files (1)
- SKILL.md
SKILL.md (first lines)
# LogOS implementer Implement the requested LogOS vNext change, keeping the patch narrow and independently verifiable. Read the existing project instructions and current code before editing. If no plan exists, make a short internal plan first and state the scope before changing files. ## Before editing 1. Read `AGENTS.md` and use `docs/README.md` to select only the active documentation relevant to the task. 2. Inspect `git status --short` and the current diff. Preserve unrelated user changes. 3. Locate the smallest responsible layer with `rg`. Reuse existing types, bounds, proof hooks, and ownership instead of introducing parallel abstractions. 4. Re-check that the requested behavior belongs in the current milestone. Do not pull deferred runtime, service, IPC, capability, allocation, or user-mode work into the Core without explicit scope. ## Implementation rules - Preserve `no_std`, fixed-size resource bounds, UEFI bootability, and QEMU debug-console output. - Keep `src/main.rs` limited to UEFI entry, `src/lib.rs` as the Core façade, and `src/scheduler.rs` as the host-tested scheduler state machine unless the task explicitly changes ownership. - Prefer the smallest change at the narrowest responsible layer. Avoid speculative APIs, generic abstractions, new runtime or OS dependencies, and unrelated cleanup. - Add or update the smallest relevant host test for behavior. Keep proof workloads deterministic and bounded. - Update `docs/architecture.md` only when the change creates a boundary that a proof needs documented. - Create and index an ADR only for an irreversible or cross-ring decision. Routine reversible implementation does not need one. - Do not commit, reset, discard, or rewrite unrelated work. ## Verification After Rust changes, run the project-required checks: - `cargo fmt --check` - the smallest relevant host test, then broader `cargo test` coverage when the change warrants it - `cargo clippy -- -D warnings` For UEFI, boot, QEMU, or other hardware-facing changes, also run the smallest relevant `scripts/check.ps1` or `scripts/run.ps1` path. For documentation or ADR changes, run the relevant documentation or ADR index check when available. If a required check cannot run, report the exact command and reason. Never claim a check passed based on inspection alone. ## Handoff Finish with: 1. changed files and the behavior added or corrected; 2. verification commands and results; 3. remaining issues, assumptions, or deferred follow-up; 4. a note about any user changes intentionally left untouched.
From Eresea/LogOS, MIT.
More from Eresea/LogOS
- 0.517score
planner
Eresea
Plan bounded LogOS vNext changes before implementation, including affected ownership, documentation, ADR, and verification work.
SkillBFreshness: BClaude Code +9 - 0.517score
debugger
Eresea
Diagnose and, when explicitly requested, narrowly fix LogOS vNext build, test, boot, UEFI, QEMU, scheduler, or proof failures using reproduction and evidence.
SkillBFreshness: BClaude Code +9 - 0.499score
domain-modeling
Eresea
Build and sharpen a project's domain model.
SkillBFreshness: BClaude Code +9 - 0.499score
codebase-design
Eresea
Shared vocabulary for designing deep modules.
SkillBFreshness: BClaude Code +9 - 0.499score
grilling
Eresea
Grill the user relentlessly about a plan, decision, or idea.
SkillBFreshness: BClaude Code +9 - 0.492score
pr
Eresea
Use when writing a PR body.
SkillBFreshness: BClaude Code +9 - 0.488score
implement
Eresea
Implement a piece of work based on a spec or set of tickets.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 14
- Last commit (this folder)
- Aug 18, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Eresea/LogOS
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Eresea
- 0.517score
planner
Eresea
Plan bounded LogOS vNext changes before implementation, including affected ownership, documentation, ADR, and verification work.
SkillBFreshness: BClaude Code +9 - 0.517score
debugger
Eresea
Diagnose and, when explicitly requested, narrowly fix LogOS vNext build, test, boot, UEFI, QEMU, scheduler, or proof failures using reproduction and evidence.
SkillBFreshness: BClaude Code +9 - 0.499score
domain-modeling
Eresea
Build and sharpen a project's domain model.
SkillBFreshness: BClaude Code +9 - 0.499score
codebase-design
Eresea
Shared vocabulary for designing deep modules.
SkillBFreshness: BClaude Code +9 - 0.499score
grilling
Eresea
Grill the user relentlessly about a plan, decision, or idea.
SkillBFreshness: BClaude Code +9 - 0.492score
pr
Eresea
Use when writing a PR body.
SkillBFreshness: BClaude Code +9
Cite this page
implementer skill. Agent Mart. https://agentmart.dev/skills/eresea-implementer (last updated 2026-10-24)