sync-initiative

sync-initiative is a skill for Claude Code, Codex from siarhei-belavus/agent-public. It costs 35 tokens per session (581 once invoked), scanned A, original, MIT.

A workflow tool for bringing completed work from a smaller child project back into a larger parent project’s shared records.

In plain words
What is it for?
Updating parent task graphs, recording decisions and contract changes, and deciding whether the next work is ready, blocked, or complete.
Why use it?
It prevents decisions, task statuses, and contract changes from remaining isolated in separate project files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Updating parent task graphs, recording decisions and contract changes, and deciding whether the next work is ready, blocked, or complete.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/siarhei-belavus/agent-public/sync-initiative
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.

Any agent
npx skills add siarhei-belavus/agent-public --skill sync-initiative
Clone the repo
git clone --depth 1 https://github.com/siarhei-belavus/agent-public

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 sync-initiative

README.md
[![agentmods](https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/sync-initiative/github.svg)](https://agentmods.dev/skills/siarhei-belavus/agent-public/sync-initiative)
Your own site
<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/sync-initiative"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/sync-initiative/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sync-initiative

Your own site · 80×15
<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/sync-initiative"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/sync-initiative.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 581 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00035 $0.00581
Opus 5 $0.00017 $0.00291
Sonnet 5 $0.00007 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 10d ago against content hash 8ba8506ed6ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sync-initiative 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 10d 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/atelier-workflow/sync-initiative/SKILL.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.

sync-initiative

Use after a child local loop has produced parent-truth that must be reconciled before more initiative work proceeds. The child packet may live in a different owner repo from the parent initiative packet.

Read first

  • ../references/initiative-packet-contract.md
  • ../references/initiative-workflow-contract.md
  • ../references/persistent-artifacts-contract.md
  • ../references/final-state-authoring-policy.md
  • parent initiative packet in the orchestrating repo
  • child packet including ARTIFACT_CANDIDATES.md in its declared Packet Root
  • ../../references/communication-mode.md

Responsibilities

  1. Enter initiative Status: sync_needed.
  2. Update the child row in TASK_GRAPH.md using only the canonical child statuses:
    • keep it active when more child-local work is still required
    • mark it blocked when an explicit blocker is now the governing fact
    • mark it done when the child outcome has been reconciled into parent truth
  3. Recompute untouched rows from pending to ready when dependencies clear.
  4. Fold stable child decisions into DECISIONS.md.
  5. Fold stable contract changes into CONTRACTS.md.
  6. Update UBIQUITOUS_LANGUAGE.md only when terminology changed.
  7. Append an outcome entry to SYNC_LOG.md.
  8. Update INDEX.md Next durable distill: now | later.
  9. Exit initiative Status: active.

Distill rule

  • set Next durable distill: now only when stable reusable residue is ready for a durable-memory pass before more child work
  • otherwise keep Next durable distill: later
  • durable-memory routing follows residue ownership, not automatically the parent initiative repo
  • after the last child sync, active remains the normal resting state until final distill-knowledge closes the initiative

Writing rule

Reconcile parent truth into one canonical state model. Do not preserve superseded child-status names, durable-distill fields, or ownership rules in initiative artifacts.

Do not

  • write tracked AGENTS.md directly here
  • treat sync as a second implementation phase
  • overwrite stable parent truth with tentative child-local notes
  • invent packet-state mutations outside the initiative contract
  • copy the child packet into the parent repo just to make sync easier

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. 10d ago First seen · 53 lines · 35 tokens per session scan A 8ba8506ed6ea

Subscribe to this mod's changes

sync-initiative is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 581 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 skills, from other repositories