shift-protocol

shift-protocol is a skill for Claude Code, Codex from tlangridge/agent-swarm. It costs 28 tokens per session (500 once invoked), scanned A, original, MIT.

A protocol for managing bounded work periods called shifts, from starting and assigning agents through active work, review readiness, and closing reports. Worktrees are preserved when a shift ends.

In plain words
What is it for?
Use it when coordinating recurring or multi-session agent work that needs formal start procedures, progress tracking, human review, and end-of-shift reporting.
Why use it?
It keeps agent teams organized across handoffs and makes previous context, tasks, findings, and completed work easier to carry forward.

Skill for Claude CodeCodex

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 skills/tlangridge/agent-swarm/shift-protocol
Any agent
npx skills add tlangridge/agent-swarm --skill shift-protocol
Clone the repo
git clone --depth 1 https://github.com/tlangridge/agent-swarm

Made for: Claude Code, Codex.

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 shift-protocol

README.md
[![agentmods](https://agentmods.dev/badge/skills/tlangridge/agent-swarm/shift-protocol.svg)](https://agentmods.dev/skills/tlangridge/agent-swarm/shift-protocol)
Your own site
<a href="https://agentmods.dev/skills/tlangridge/agent-swarm/shift-protocol"><img src="https://agentmods.dev/badge/skills/tlangridge/agent-swarm/shift-protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 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 $0.00028 $0.00500
Opus 5 $0.00014 $0.00250
Sonnet 5 $0.00006 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured 3d ago against content hash c3886d83101c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shift-protocol 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 3d 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.

skills/shift-protocol/SKILL.md · 61 lines

What it actually says

Shift Protocol

Shifts are bounded work periods with a defined start and end.

Shift Lifecycle

  1. Badge-in -- Agents are spawned and initialized. The lead receives a kickoff message with team roster and instructions.
  2. Active work -- Agents coordinate, create tasks, and execute work.
  3. Ready for review -- The lead marks the shift as ready for human review when all planned work is done.
  4. Badge-out -- The shift ends, agents are terminated, worktrees are preserved.

At Shift Start (Lead)

  1. Read existing context: swarm context
  2. Check current tasks: swarm tasks
  3. Read the previous shift's close report if available: swarm read close-report.md
  4. If there are existing tasks, assess what needs to be done
  5. If there are no tasks, wait for the user's mission, then break it into tasks and assign them
  6. Send clear instructions to each worker agent

At Shift Start (Worker)

  1. Check for tasks: swarm tasks --mine
  2. If no tasks, stand by and wait for the lead
  3. Read context when available: swarm context
  4. Read shared findings: swarm read findings.md

During Active Work

  • Lead monitors progress with swarm activity
  • Workers execute tasks and report progress
  • Discoveries are shared via swarm append findings.md --content "..."
  • Blockers are escalated immediately

Shift Closing (Lead)

When all planned work is done:

  1. Verify all tasks are marked done or have clear status
  2. Ensure all branches are pushed and PRs are created
  3. Write a shift summary: swarm write close-report.md with:
    • What was accomplished
    • What is still pending
    • Key decisions made
    • Known issues or risks
  4. Mark the shift as ready for review: swarm shift review "Summary of accomplishments"

Reading Previous Shift Reports

At the start of a new shift, always check for a previous close report:

swarm read close-report.md

This provides continuity between shifts and prevents re-doing completed work.

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. 3d ago First seen · 61 lines · 28 tokens per session scan A c3886d83101c

Subscribe to this mod's changes

shift-protocol is a skill published in the GitHub repository tlangridge/agent-swarm (5 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 500 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens