What is compact-task-memory?

A task-memory cleanup command that condenses TASK_STATE.md after it becomes too large to use comfortably. It keeps important decisions and the next recommended step while removing outdated or routine details.

Use it to shrink an engineering task’s working state while retaining its operational truth.

It reduces the amount of task history an agent must read when resuming work. The removed prose remains traceable through version history and an audit log.

compact-task-memory — Command for Claude Code by Mozurok/fhorja.dev

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/Mozurok/fhorja.dev

Made for: Claude Code.

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/commands/mozurok/fhorja.dev/compact-task-memory/github.svg)](https://agentmods.dev/commands/mozurok/fhorja.dev/compact-task-memory)

Your own site

<a href="https://agentmods.dev/commands/mozurok/fhorja.dev/compact-task-memory"><img src="https://agentmods.dev/badge/commands/mozurok/fhorja.dev/compact-task-memory/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/commands/mozurok/fhorja.dev/compact-task-memory"><img src="https://agentmods.dev/badge/commands/mozurok/fhorja.dev/compact-task-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 104 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,967 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	$0.00104	$0.04967
Opus 5.5	$0.00042	$0.01987
Sonnet 5.5	$0.00021	$0.00993
Haiku 4.5	$0.00010	$0.00497

Measured 12d ago against content hash 7563b99a89c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

compact-task-memory 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 12d 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.

commands/compact-task-memory.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

compact-task-memory

Act as a senior/staff engineering workflow memory compactor for the active engineering task.

Goal: Produce a compaction summary of TASK_STATE.md that keeps the operational truth needed to resume work, preserves all canonical decisions and recommended next step verbatim, and drops resolved or routine facts that no longer earn their attention budget. Lossy on the prose but provenance-preserving: every dropped fact stays recoverable from the pre-compaction snapshot (ADR-0141) AND traceable to the append-only .wos/VERIFICATION_LOG.jsonl audit chain, which this command never rewrites (per ADR-0093).

Mandatory context bootstrap (before any output):

Read these sections in WORKFLOW_OPERATING_SYSTEM.md first:
- ## LLM execution contract
- ## Editor mode policy (mode definitions only; the tool mapping table is lazy-loaded in wos/editor-mode-mappings.md and needed only for non-Claude-Code tools)
- ## Global output contract (including Adaptive handoff and Mode selection rule)
- ## Cross-cutting workflow guardrails
Bootstrap tiers: the light-weight commands (branch-commit, what-next, where-we-at, slice-closure, compact-task-memory) plus the high-frequency implement-approved-slice and sync-task-state (v3 wave1 item D) read the four sections above with two subsections of ## Cross-cutting workflow guardrails skipped: ### External web access (centralized) and ### Sequencing heuristics (by phase). Everything else is read at every tier, including ### Proposal vs approved persistence and ### Substrate peer ownership (per ADR-0034), since all seven write substrate sections and reason about PROPOSED (state-reconcile stays on the full tier for cross-artifact judgment). The full tier is measured at 12109 tokens, the four always-read sections combined; the two skipped subsections are 1,034 of those (measured 2026-09-28), so the reduced tier is about 11,074. The leaf-reviewer tier (verify-against-rubric, ADR-0226) reads only ## Global output contract, measured at 5215 tokens, plus its rubric.
Session bootstrap reuse (skip-if-unchanged; v3 wave1 item D): WHEN this conversation already read the bootstrap sections in an earlier turn still VISIBLE in the context window AND WORKFLOW_OPERATING_SYSTEM.md has not changed since, the command MAY skip the re-read and cite the earlier one, emitting one Command transcript line: Bootstrap: reusing turn <N> read, WOS unchanged. Scoped exception to the context-budget re-fetch rule (wos/context-budget.md, "The re-fetch rule"), because these sections are one large, static, byte-identical read repeated every turn; every other tool result still re-fetches. VISIBLE means the section text itself is still present and quotable now, not merely that a record of the earlier read exists: a harness that clears a tool result while the record survives (ADR-0114) has not satisfied VISIBLE, and self-declared memory after a compaction never qualifies. A stateless-per-turn harness is excluded. The transcript line is mandatory; a silent skip is invalid output.
Resolving the spec and wos/<topic>.md: canonical repository FIRST. Otherwise use active-adapter docs: ~/.claude/workflow-docs (CLAUDE_WORKFLOW_DOCS_DIR), ~/.cursor/workflow-docs (WORKFLOW_DOCS_DIR; project .cursor/workflow-docs on project installs), ~/.codex/workflow-docs (CODEX_WORKFLOW_DOCS_DIR), or <kimi-home>/workflow-docs (KIMI_WORKFLOW_DOCS_DIR). Nonempty overrides win. Kimi home: KIMI_CODE_HOME, else existing ~/.kimi-code, else existing ~/.kimi, default ~/.kimi-code. Use one root for both paths; try other adapters if absent or unknown. Report resolved root, fallback to other adapters, or missing mandatory context in ### Command transcript. Installed snapshots refresh and prune retired topics only on sync.
Read additional sections only when relevant to this command's role.
Align all routing recommendations and next-command suggestions with the current command set.
Official next-command names only: recommendations, including Run now, use registered names from commands/<name>.md or commands/<name>/SKILL.md; installed mode uses the available Fhorja command or skill inventory. No invented aliases. Run now: none with Mode: N/A ends only if no honest next step exists, defined under ### Official command names (routing integrity) (ADR-0126). Required inputs:
active task folder path
TASK_STATE.md (current; the file being compacted)
DECISIONS.md (read-only; canonical decisions must be preserved verbatim)
IMPLEMENTATION_PLAN.md (read-only; recommended-next-step must trace to a slice in the plan)
SLICES/*.md (read-only; closed slices are durable, NOT compacted; slice notes outside TASK_STATE survive)

Read the full file on GitHub · 157 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.

12d ago Changed · -71 tokens per session 7563b99a89c6
15d ago Changed · -1 lines 687992072e08
22d ago Changed · -1 lines f1e2799f5597
23d ago Changed · -2 lines d3adeb30da8b
1mo ago First seen · 161 lines · 175 tokens per session scan A 4c7ee57a695a

Subscribe to this mod's changes

compact-task-memory is a command published in the GitHub repository Mozurok/fhorja.dev (10 stars, last pushed 12d ago), licensed MIT. It adds 104 tokens to every session and 4,967 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.

Claude Code Memory and context agent-skills ai-coding cursor developer-tools spec-driven-development

compact-task-memory

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

compact-task-memory

What this file has done since we first saw it

Other commands, from other repositories

kiro-steering-custom

kiro-steering

steering

consolidate

memory-audit

memory-why