active-memory-reminder
Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable).
Skill by Archive228
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/archive228-active-memory-reminder
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/active-memory-reminder
What's inside
- Skill name
active-memory-reminder- Description
- Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop.
- License
- MIT
- Instructions
- 51 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Active Memory Reminder
Loopkit splits shift-notes across two files on purpose:
- **`claude-progress.txt`** — free-form prose. Human-readable narrative of what the last session did, what is in flight, what to pick up next. Wins for context and intent. Loses when the model needs to *decide* whether a decision was made.
- **`claude-decisions.json`** — machine-readable array of `{ts, decision}` entries, appended by the loopkit `pre-compact` hook every time the transcript is about to be compacted. Wins for durability of specific choices ("chose Postgres over SQLite because…", "rejected the polling approach", "tried htmx and switched to Alpine").
Compaction is where reasoning dies. The summarizer keeps the shape of the work but strips the *why*. `claude-decisions.json` is the durable side-channel that survives that. This is the same pattern Meta's NapMem paper calls out for behavioral-state-decay in long-running agents: prose degrades faster than structured facts because the model rewrites prose freely and edits structured data carefully (also why loopkit uses JSON for `feature_list.json`; see [[feature-list-json]]).
## When to apply
- **Session start / post-/clear / post-compact.** Read `claude-decisions.json` right after `claude-progress.txt` and before you look at code. If both files disagree, the JSON is the more recent hard record of a specific choice; the prose gives you the reason.
- **Before re-litigating a design choice.** If you're about to propose "let's use X instead of Y," grep `claude-decisions.json` first. If a prior session already rejected X and wrote it down, don't burn the token budget re-deriving that.
- **When picking up mid-implementation work.** Decisions frame constraints the progress file may not restate.
## File contract
`claude-decisions.json` is a JSON array. Every entry is `{ts, decision}`:
```json
[
{"ts": "2026-07-14T18:22:09Z", "decision": "chose Playwright MCP over Puppeteer because Puppeteer's alert-modal blind spot bit us in run 41"},
{"ts": "2026-07-14T20:04:11Z", "decision": "rejected the daemon-per-project approach; switched to a single supervisor with per-project subdirs"},
{"ts": "2026-07-15T09:31:44Z", "decision": "tried and failed to cache the plan across sessions — plan went stale within two sessions, dropped"}
]
```
Constraints:
- Append-only in normal operation. The `pre-compact` hook appends; sessions read.
- You MAY add a decision by hand if you make one mid-session that the hook won't catch (e.g., a decision made in code, not prose). Use the same shape. Do not rewrite or delete existing entries — they are the durable record.
- If entries contradict, newer wins, but note the contradiction in `claude-progress.txt` so the reason is captured.
## The hook
`.claude/hooks/pre-compact` runs on both manual (`/compact`) and auto compaction. It skims the transcript for phrases matching `decided|chose|rejected|tried and failed|switched from .* to|going with|not going to`, dedupes, caps at 20 per compaction, timestamps each, and appends. It is silent-safe: any failure logs to stderr and exits 0 so compaction is never blocked.
## Anti-patterns
- **Reading `claude-progress.txt` and skipping `claude-decisions.json`.** You will re-open settled questions. The prose file often omits *why we didn't do the other thing* — that's what the JSON is for.
- **Editing or deleting past decisions to "clean them up."** Same rule as `feature_list.json` steps and descriptions: durable structured records are load-bearing. Contradict them in a new entry; don't erase the old one.
- **Storing prose in `claude-decisions.json`.** It is not a second progress file. Entries are single decisions with a timestamp, nothing else.
- **Assuming the hook caught it.** The regex catches most decisions but not all. If you made a decision the transcript won't obviously match, add it by hand before ending the session.
## Related
- [[progress-reading-protocol]] — session-opening sequence; step 2b reads this file.
- [[feature-list-json]] — the other structured-over-prose file loopkit relies on.
- [[shift-notes]] — the prose companion this file is paired with.
- [[clean-state-contract]] — session-end discipline that keeps the pairing usable.From Archive228/loopkit, MIT.
More from Archive228/loopkit
- 0.701score
structured-output
Archive228
Get JSON out of the model reliably.
SkillCFreshness: C★ 755Claude Code +9 - 0.701score
prompt-caching
Archive228
Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn.
SkillCFreshness: C★ 755Claude Code +9 - 0.701score
using-loopkit
Archive228
Use when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY…
SkillCFreshness: C★ 755Claude Code +9 - 0.701score
hitl-escalate
Archive228
Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
feature-list-json
Archive228
Enumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
pdf-ingestion
Archive228
Get a PDF into the model without blowing the context window or losing structure.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
planner-spec-expand
Archive228
Expand a 1-4 sentence product brief into a full spec with a design language, acceptance surface, and an ordered feature list.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
adversarial-verify
Archive228
Review a diff against the goal spec assuming the code is BROKEN.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
init-script-contract
Archive228
Author idempotent init.sh under 120s plus sibling test.sh, stop.sh, reset.sh, serve.sh with fixed names the harness relies on.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
broken-window-check
Archive228
Before picking new work, smoke-test the last "completed" feature.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
harness-stripping
Archive228
Systematically remove one harness component at a time and measure impact, killing scaffolding that no longer earns its complexity.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
eval-harness
Archive228
Build a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed.
SkillCFreshness: C★ 755Claude Code +9
Signals
- Stars
- 755
- Forks
- 124
- Open issues
- 0
- Last commit (this folder)
- Jul 14, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Archive228/loopkit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Archive228
- 0.701score
structured-output
Archive228
Get JSON out of the model reliably.
SkillCFreshness: C★ 755Claude Code +9 - 0.701score
using-loopkit
Archive228
Use when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY…
SkillCFreshness: C★ 755Claude Code +9 - 0.701score
hitl-escalate
Archive228
Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop.
SkillCFreshness: C★ 755Claude Code +9 - 0.701score
prompt-caching
Archive228
Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
harness-stripping
Archive228
Systematically remove one harness component at a time and measure impact, killing scaffolding that no longer earns its complexity.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
evaluator-calibration
Archive228
Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.
SkillCFreshness: C★ 755Claude Code +9
Cite this page
active-memory-reminder skill. Agent Mart. https://agentmart.dev/skills/archive228-active-memory-reminder (last updated 2026-10-24)