light-implementer
Execute one approved light slice exactly as its packet states, verified by the packet's deterministic command.
Skill by alphazede
Chalk Labs
Need help deploying light-implementer?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/alphazede-light-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
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 and code. Checked Oct 26, 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/light-implementer
What's inside
- Skill name
light-implementer- Description
- Execute one approved light slice exactly as its packet states, verified by the packet's deterministic command. Use for Light Implementer, light, mechanical, scaffold, bind, assemble, regenerate, or runbook packets. Do not use for judgement work, authoring, repair, review, or any decision.
- License
- Apache-2.0
- Instructions
- 49 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Light Implementer
Use only when enabled in the selected profile and assigned the mechanical slice.
Inputs fully determine the output, a
command decides pass or fail, and nothing is decided in-session.
Loop: execute exact packet → deterministic self-check → return evidence or typed failure.
## Inputs and match
- **Inputs:** the Implementer packet contract (baseline, objective, exact write
set, authority, commands, stop rule, return schema, visible wave receipt,
profile identity from the recorded snapshot) for a slice whose
`work_class` is `light`.
- **Match:** every criterion holds:
1. Inputs are all named and present: paths, digests, UIDs, a runbook.
Nothing is discovered or interpreted.
2. The transformation is mechanical: copy, assemble, format, fill a
template, append rows, run a documented command, record its output.
3. The packet names the command whose exit status verifies the output.
4. No decision: no value chosen, ambiguity resolved, candidate selected,
requirement, contract, rationale, or verification case written.
5. Bounded blast radius: one write set, no product source, no host or
runtime mutation beyond a documented read-only or prepare call.
- **Non-match:** a `judgement` slice; a packet whose LOOP says repair your
own findings; an `[OPEN]` value; a register conflict to weigh.
## Algorithm
1. Revalidate the checkout lease exactly as the Implementer does. On mismatch
return `WAITING_ON` without writing.
2. Do exactly what the packet states, inside the write set, and nothing else.
3. Run the packet's verification command at the candidate revision. Record
exit status, output digest, and changed paths. Any deterministic-verification
receipt is diagnostic only and never satisfies an assurance gate.
4. If any step needs a choice the packet did not make, stop before writing
further and return `NEEDS_MORE_EVIDENCE` with `reclassify: judgement`
and the exact question. Never guess, never escalate silently.
5. There is no in-wave repair loop. A failing command returns the typed
failure with its output; the Orchestrator decides.
## Return and recovery
Return `CANDIDATE_READY`, `NEEDS_MORE_EVIDENCE`, `WAITING_ON`, or
`OWNER_DECISION_REQUIRED` with verdict, candidate_ref, changed_paths, tests,
findings, blocker, and `reclassify` when set.
Never author, repair, self-certify, expand the write set, or publish.From alphazede/bearing-lite, Apache-2.0.
More from alphazede/bearing-lite
- 0.609score
architectural-alignment
alphazede
Establish architectural fit and resolve material scope decisions after Intake is confirmed.
SkillAFreshness: A★ 3Claude Code +9 - 0.609score
integration-engineer
alphazede
Author selected integration planning inputs, or perform explicitly requested independent assessment of an integrated candidate.
SkillAFreshness: A★ 3Claude Code +9 - 0.609score
reviewer
alphazede
Independently review one exact stable candidate for introduced actionable defects in a fresh session at the configured cadence boundary.
SkillAFreshness: A★ 3Claude Code +9 - 0.606score
prompt
alphazede
Compose one bounded handoff for an already selected agent role and session.
SkillAFreshness: A★ 3Claude Code +9 - 0.606score
requirements-engineer
alphazede
Author requirements and acceptance criteria for selected planning work after scope is settled.
SkillAFreshness: A★ 3Claude Code +9 - 0.606score
bearing-lite
alphazede
Coordinate a Bearing lifecycle as Planning or Implementation Orchestrator only when the owner explicitly requests Bearing for that mode.
SkillAFreshness: A★ 3Claude Code +9 - 0.606score
planning-and-design
alphazede
Perform final planning/design in the Planning Orchestrator's current session after the selected specialists return.
SkillAFreshness: A★ 3Claude Code +9 - 0.606score
onboard-bearing
alphazede
Guided first-run and later configuration of profiles.json.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
implementer
alphazede
Implement one approved bounded packet in an exact write set.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
systems-modeler
alphazede
Select modeling mode and attach view metadata in the planning wave before design finalization.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
coordinator
alphazede
Coordinate one approved implementation wave only when enabled in the selected profile and assigned that wave.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
intake
alphazede
Verify and propose one target repository and plan directory when repository identity is absent or ambiguous.
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 1
- Open issues
- 9
- Last commit (this folder)
- Oct 18, 2026 (12 days ago)
- Last release
- Oct 21, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/alphazede/bearing-lite
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from alphazede
- 0.609score
reviewer
alphazede
Independently review one exact stable candidate for introduced actionable defects in a fresh session at the configured cadence boundary.
SkillAFreshness: A★ 3Claude Code +9 - 0.609score
integration-engineer
alphazede
Author selected integration planning inputs, or perform explicitly requested independent assessment of an integrated candidate.
SkillAFreshness: A★ 3Claude Code +9 - 0.609score
architectural-alignment
alphazede
Establish architectural fit and resolve material scope decisions after Intake is confirmed.
SkillAFreshness: A★ 3Claude Code +9 - 0.606score
onboard-bearing
alphazede
Guided first-run and later configuration of profiles.json.
SkillAFreshness: A★ 3Claude Code +9 - 0.606score
bearing-lite
alphazede
Coordinate a Bearing lifecycle as Planning or Implementation Orchestrator only when the owner explicitly requests Bearing for that mode.
SkillAFreshness: A★ 3Claude Code +9 - 0.606score
planning-and-design
alphazede
Perform final planning/design in the Planning Orchestrator's current session after the selected specialists return.
SkillAFreshness: A★ 3Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get light-implementer running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
light-implementer skill. Agent Mart. https://agentmart.dev/skills/alphazede-light-implementer (last updated 2026-10-24)