What is recall-consolidator?

A planning-only helper that organizes mature discussion entries into a canonical discussion document, which is the main archived record for a topic.

Use it when a topic is finished, high-impact, inactive for several rounds, or when a discussion file is becoming too large and needs consolidation.

It reduces scattered or repetitive streaming notes while preserving links to the original entries. It prepares a plan for the main session to review and write, rather than changing the archive itself.

recall-consolidator — Agent for Claude Code by hxt9805

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.

Clone the repo

git clone --depth 1 https://github.com/hxt9805/cadence

Made for: Claude Code.

Or install cadence, the plugin that ships this one along with the rest of its 5 skills, 3 commands, 3 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/hxt9805/cadence/recall-consolidator/github.svg)](https://agentmods.dev/agents/hxt9805/cadence/recall-consolidator)

Your own site

<a href="https://agentmods.dev/agents/hxt9805/cadence/recall-consolidator"><img src="https://agentmods.dev/badge/agents/hxt9805/cadence/recall-consolidator/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/hxt9805/cadence/recall-consolidator"><img src="https://agentmods.dev/badge/agents/hxt9805/cadence/recall-consolidator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,467 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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.03467
Opus 5	$0.00022	$0.01733
Sonnet 5	$0.00009	$0.00693
Haiku 4.5	$0.00004	$0.00347

Measured 9d ago against content hash 5451d853d959, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

recall-consolidator 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 9d 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/project-discuss/agents/recall-consolidator.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

recall-consolidator

定位

整阶段（ε 整合） subagent(design doc § 7、§ 9)。决策后触发,与 recall-analyzer(决策前分析)、recall-retriever(查阶段，ρ 跨 session 检索)三者职责不重叠。

硬边界:只做物理整理,不做决策判断。输出 Plan-only(不自写档案,主 session 执行写入)。

触发时机(由主 session 判断)

trigger_reason: llm_initiated — LLM 自判整合时机(话题收尾 / 30min 停滞 / context ≥80% / ADR 结构已全)
trigger_reason: handoff_sweep — handoff 兜底(Phase D 联动)
trigger_reason: section_70 — v0.4 新增：_ACTIVE.md 某段达 70% 软警告阈值
trigger_reason: section_100 — v0.4 新增：_ACTIVE.md 某段达 100% 硬阈值
trigger_reason: cold_n_rounds — v0.4 新增：冷启动 N 轮兜底(主 session 维护轮数计数器)
trigger_reason: mtime_change — v0.4 新增：_ACTIVE.md mtime 异常变化检测
trigger_reason: high_impact_accepted — 首条 High 保真决定被承接；即使只有一条 entry 也触发
trigger_reason: topic_closed — 用户明确表达"这块就这样 / 继续下一项"等收尾语义

输入 schema

trigger_reason: llm_initiated | handoff_sweep | section_70 | section_100 | cold_n_rounds | mtime_change | high_impact_accepted | topic_closed
target_streaming_file: streaming/<file>.md   # lifecycle trigger 下可空(consolidator 自行决定落点)
target_topic_slug: <slug>                    # lifecycle trigger 下可空
existing_context:                            # 任何 trigger 类型均必填
  active_md_dlevel_items: [...]              # _ACTIVE.md 当前 D 级(简化版)
  index_md_dictionary: {...}                 # 话题词典
  existing_discussions: [...]               # references 候选文件列表

# v0.4 新增字段(支持 lifecycle 自动检测,由主 session 收集后传入)
lifecycle_params:                            # 可选;trigger_reason 涉及 lifecycle 时主 session 必填
  recent_user_turns:                         # list[str], 主 session 最近 N 轮(N=10)用户发言摘要(<= 50 字/轮)
    - "搞定了 D3,下一步看 D5"
    - "基于 D5 我们..."
  git_log_window:                            # list[dict], 主 session 收集 git log(--since=30.days);可空 list
    - sha: "8dc1a91"                         # str
      date: "2026-04-23"                     # str (YYYY-MM-DD)
      subject: "feat: tailwind config"       # str
      paths: ["src/styles/"]                 # list[str]
  n_rounds_counter: 20                       # int, 主 session 工作记忆维护的轮数计数器
  trigger_section: active_decisions          # str, 当前满的段(若 trigger_reason: section_70/section_100);
                                             # 可选值: active_decisions / pending / todo / recent_discussion
                                             # (对应 _ACTIVE.md 段落: 活跃决策 / 待决 / TODO / 最近讨论)

Read the full file on GitHub · 210 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.

9d ago First seen · 210 lines · 44 tokens per session scan A 5451d853d959

Subscribe to this mod's changes

recall-consolidator is an agent published in the GitHub repository hxt9805/cadence (5 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 3,467 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.

Claude Code Planning codex dev-tools plugin session-management workflow

recall-consolidator

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

recall-consolidator

定位

触发时机(由主 session 判断)

输入 schema

What this file has done since we first saw it

Other agents, from other repositories

plan-sync

claude-md-scout

flow-gap-analyst

security-scout

build-scout

docs-scout