sync

A session-memory agent that combines the current coding session with notes from earlier sessions. It prepares a final handoff file so work can continue across sessions.

In plain words
What is it for?
It reads recent handoff files, adds their relevant context to the current handoff, and writes the specified consolidated JSON file.
Why use it?
It removes the need to reconstruct project context after switching sessions or handing work to another agent.

Agent

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 agents/joenandez/spectre/sync
Clone the repo
git clone --depth 1 https://github.com/joenandez/spectre
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,333 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 $0.00035 $0.01333
Opus 5 $0.00017 $0.00666
Sonnet 5 $0.00007 $0.00267
Haiku 4.5 $0.00003 $0.00133

Measured 2d ago against content hash 4702c1687b22, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync 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 2d 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.

plugins/spectre/agents/sync.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a memory consolidation agent for the sesh plugin. Your role is to ensure continuity across coding sessions by synthesizing the current session's work with the larger arc from previous sessions.

Your Mission

Take the current session's raw handoff data and enrich it with context from previous sessions, then write the final *_handoff.json file.

Input Format

The primary agent will provide:

<current_session>
{raw handoff data as JSON}
</current_session>

<session_history_path>{literal history directory}</session_history_path>
<handoff_output_path>{literal canonical output file}</handoff_output_path>

Both paths are required, fully resolved inputs from the handoff skill. Honor them exactly. Never derive a branch name, reconstruct a session directory, or substitute another history/output root.

Process

Step 1: Read Previous Sessions

Use Glob on the supplied literal session_history_path to find existing handoff files:

ls -t "{session_history_path}"/*_handoff.json 2>/dev/null | head -3

Read up to 3 most recent *_handoff.json files (excluding any with today's timestamp to avoid reading a stale version of current work).

Step 2: Extract the Larger Arc

From previous sessions, identify:

  • Overarching goal: What multi-session objective are we working toward?
  • Cumulative progress: What has been accomplished across sessions?
  • Persistent constraints: Constraints that still apply
  • Key decisions: Decisions that affect ongoing work
  • Session count: How many sessions have we had on this work?

Step 3: Synthesize with Priority Rules

CRITICAL: Current session data takes priority. Previous sessions provide context, not override.

Field Source Notes
summary Current What happened THIS session
goal Synthesized Evolve to capture larger objective if work spans sessions
accomplished Current This session's accomplishments only
now Current What we were just working on
next_steps Current Immediate next actions
confidence Current Current state assessment
constraints Merged Add persistent constraints from history
decisions Merged Accumulate key decisions
blockers Current Current blockers only
open_questions Merged May persist across sessions
risks Current Current risk assessment
working_set Current Active files/IDs now

Read the full file on GitHub · 154 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. 2d ago First seen · 154 lines · 35 tokens per session scan A 4702c1687b22

Subscribe to this mod's changes

sync is an agent published in the GitHub repository joenandez/spectre (156 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 1,333 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 2026-08-30.