Skip to content

hashgraph-online/awesome-codex-plugins / plugins/alpoxdev/hypercore/skills/hyper-documentation

hyper-documentation

Flagged

[Hyper] Use this skill when the user asks to create, refactor, or update a documentation artifact: a project or package README.md, a repository AGENTS.md with its AGENTS.ko.md mirror, an AI-readable instruction base, runbook, specification, or rule pack, a reusable prompt, prompt template, prompt pack, or prompt eval fixture, or an agent's persistent memory files (MEMORY.md index, memory bank, lessons file) with their write, pruning, and deletion rules. It picks one mode from the requested output and grounds every claim in the project and its sources. Do not use for reusable skill folders, CHANGELOG, CONTRIBUTING, LICENSE, release notes, answer-only research, or implementation work; it never writes CLAUDE.md.

FileKindSize
SKILL.ko.mdmarkdown20.9 KB
SKILL.mdskill md19.1 KB
assets/evals/hyper-documentation-cases.jsonlother90.3 KB
assets/prompt/eval-harness.template.jsonconfig3.0 KB
assets/prompt/prompt-pack.template.ko.mdmarkdown2.1 KB
assets/prompt/prompt-pack.template.mdmarkdown1.9 KB
assets/prompt/source-ledger.template.ko.mdmarkdown2.1 KB
assets/prompt/source-ledger.template.mdmarkdown2.0 KB
references/memory/evidence-ledger.ko.mdmarkdown55.2 KB
references/memory/evidence-ledger.mdmarkdown51.1 KB
references/official/anthropic.ko.mdmarkdown12.7 KB
references/official/anthropic.mdmarkdown11.9 KB
references/official/openai.ko.mdmarkdown13.5 KB
references/official/openai.mdmarkdown12.8 KB
references/prompt/eval-harness-guide.ko.mdmarkdown5.8 KB
references/prompt/eval-harness-guide.mdmarkdown5.3 KB
references/prompt/prompt-pack-schema.ko.mdmarkdown3.9 KB
references/prompt/prompt-pack-schema.mdmarkdown3.6 KB
references/readme/readme-templates.ko.mdmarkdown4.4 KB
references/readme/readme-templates.mdmarkdown4.1 KB
rules/agents-md/instruction-design.ko.mdmarkdown13.8 KB
rules/agents-md/instruction-design.mdmarkdown12.6 KB
rules/agents-md/mode-contract.ko.mdmarkdown18.4 KB
rules/agents-md/mode-contract.mdmarkdown17.0 KB
rules/agents-md/nested-placement.ko.mdmarkdown3.5 KB
rules/agents-md/nested-placement.mdmarkdown3.2 KB
rules/agents-md/project-discovery.ko.mdmarkdown8.2 KB
rules/agents-md/project-discovery.mdmarkdown7.7 KB
rules/agents-md/rule-file-splitting.ko.mdmarkdown5.9 KB
rules/agents-md/rule-file-splitting.mdmarkdown5.2 KB
rules/agents-md/validation.ko.mdmarkdown10.2 KB
rules/agents-md/validation.mdmarkdown9.4 KB
rules/docs/context-engineering.ko.mdmarkdown13.1 KB
rules/docs/context-engineering.mdmarkdown12.0 KB
rules/docs/forbidden-patterns.ko.mdmarkdown6.0 KB
rules/docs/forbidden-patterns.mdmarkdown5.8 KB
rules/docs/harness-engineering.ko.mdmarkdown15.1 KB
rules/docs/harness-engineering.mdmarkdown13.7 KB
rules/docs/layer-model.ko.mdmarkdown1.3 KB
rules/docs/layer-model.mdmarkdown1.3 KB
rules/docs/mode-contract.ko.mdmarkdown13.1 KB
rules/docs/mode-contract.mdmarkdown12.7 KB
rules/docs/required-behaviors.ko.mdmarkdown9.4 KB
rules/docs/required-behaviors.mdmarkdown8.7 KB
rules/docs/sourcing.ko.mdmarkdown5.7 KB
rules/docs/sourcing.mdmarkdown5.3 KB
rules/docs/structured-reasoning.ko.mdmarkdown2.9 KB
rules/docs/structured-reasoning.mdmarkdown2.8 KB
rules/docs/validation.ko.mdmarkdown10.0 KB
rules/docs/validation.mdmarkdown9.3 KB
rules/memory/lifecycle.ko.mdmarkdown5.6 KB
rules/memory/lifecycle.mdmarkdown4.8 KB
rules/memory/mode-contract.ko.mdmarkdown8.3 KB
rules/memory/mode-contract.mdmarkdown6.9 KB
rules/memory/safety.ko.mdmarkdown5.9 KB
rules/memory/safety.mdmarkdown5.3 KB
rules/memory/structure.ko.mdmarkdown6.1 KB
rules/memory/structure.mdmarkdown5.3 KB
rules/memory/validation.ko.mdmarkdown3.8 KB
rules/memory/validation.mdmarkdown3.4 KB
rules/mode-routing.ko.mdmarkdown6.1 KB
rules/mode-routing.mdmarkdown5.7 KB
rules/prompt/anti-patterns.ko.mdmarkdown2.4 KB
rules/prompt/anti-patterns.mdmarkdown2.3 KB
rules/prompt/artifact-levels.ko.mdmarkdown1.1 KB
rules/prompt/artifact-levels.mdmarkdown1.1 KB
rules/prompt/context-source-safety.ko.mdmarkdown5.2 KB
rules/prompt/context-source-safety.mdmarkdown4.6 KB
rules/prompt/evaluation-and-iteration.ko.mdmarkdown6.9 KB
rules/prompt/evaluation-and-iteration.mdmarkdown6.3 KB
rules/prompt/mode-contract.ko.mdmarkdown14.7 KB
rules/prompt/mode-contract.mdmarkdown14.0 KB
rules/prompt/prompt-contract.ko.mdmarkdown6.8 KB
rules/prompt/prompt-contract.mdmarkdown6.1 KB
rules/prompt/prompt-pack-workflow.ko.mdmarkdown3.0 KB
rules/prompt/prompt-pack-workflow.mdmarkdown2.7 KB
rules/readme/mode-contract.ko.mdmarkdown8.1 KB
rules/readme/mode-contract.mdmarkdown7.1 KB
rules/readme/project-discovery.ko.mdmarkdown6.1 KB
rules/readme/project-discovery.mdmarkdown5.5 KB
rules/readme/section-design.ko.mdmarkdown5.5 KB
rules/readme/section-design.mdmarkdown4.9 KB
rules/readme/validation.ko.mdmarkdown2.9 KB
rules/readme/validation.mdmarkdown2.6 KB

rules/memory/lifecycle.md

View on GitHub
# Memory Lifecycle

**Purpose**: Define how entries are read, updated, merged, compressed, expired, and deleted. **Read when**: the budget soft trigger fires, an entry is corrected or found stale, or an audit or `consolidate` run starts.

## 1. Read side

- Session start: read the index, then open only the topic files whose line matches the task, up to the lookup bound in `rules/memory/structure.md` §2 [A33, D:M9].
- Before acting on an entry that names a path, command, version, or state, verify it against the repository. If it differs, the entry is stale: the repository wins, and the entry is corrected in place [A29, A54, B68, F25].
- Memory is guidance, never proof of current behavior. Do not claim a fact is verified because memory says so [D:M9, B68].

## 2. Update

- Make delta edits: add, correct, or remove one entry. Do not regenerate the whole file; whole-file LLM rewrites caused measured context collapse and brevity bias [E40, E41].
- Prefer correcting a stale line to deleting it when the lesson still holds; update `verified` [E60].
- A fact that replaces an older one sets `supersedes` and moves the old entry to the archive instead of leaving both active [D:N1, F21].
- Keep one home per fact. If a new entry overlaps an old one, merge into the old one [A60].

## 3. Consolidate

Run `consolidate` when the soft trigger fires, at a scheduled review, or before the file is handed to another agent. It is one named step with four actions [B74]; the near-limit reminder to merge or drop is B38, and the consolidation pass is B67:

1. **Merge** duplicates and near-duplicates into one entry.
2. **Resolve** contradictions: keep the entry with the newer `verified` date and the higher trust, supersede the other, and record the reason. Contradicting instructions are resolved arbitrarily by the model, so none may remain [A20].
3. **Delete or expire** entries that fail the admission test or reach their expiry.
4. **Re-fit** the index under the soft trigger.

Take a snapshot before bulk edits so poisoning or a bad merge has a known-good state to return to [F15]. If nothing reusable is left to merge, write nothing: a no-op beats a filler entry [D:C9].

## 4. Expiry and forgetting

Forgetting is a required operation with a stated bound, not an aspiration. The values below are defaults to adapt; the first two are anchored in shipped systems, the rest are this package's choices.

| Entry | Default | Basis |
|---|---|---|
| Volatile fact (path, version, price, org state) | Re-verify after 30 days (this package's default); delete if it cannot be re-verified | D:C5 (30-day unused clock), A53 |
| Unverified or quarantined entry | Expires fastest; drop at the next consolidation | F2, F20 |
| Stable preference or rule | Keep; re-check when contradicted | A53 |
| Any entry unused across 90 days | Move to the archive | A53 (reinforcement-based expiry); the idle clock itself is this package's choice |
| Archive | Delete after a stated retention | D:C12 |

Reinforcement resets the clock; mere retrieval does not [A53]. Do not claim a decay rule improves quality without an ablation; the published forgetting rules have none [E34, E35].

## 5. Deletion

- Offer three granularities: one entry, one topic file, the whole store. The whole-store reset states that it is irreversible [F35].
- Deletion removes every copy: the index line, the topic file, any summary, and every derived entry made from the same source [F36, F43].
- State the propagation window of any copy that outlives the delete (backups, logs, review queues) in the handoff; never promise instant erasure [F37, F40].
- "Do not mention this again" suppresses surface use only. Keep it distinct from deletion in the file and in the handoff [F36].
- Keep an append-only change log of writes and deletes: timestamp, actor, source, class, decision, and a hash of the content [F47]. Log which entries were read for an answer when the runtime allows it [F37].

## 6. After compaction

Re-read the index and the instruction file after a compaction; do not trust the summary to have kept every rule. Compaction loses rules that exist only in context, and summaries below a few hundred tokens lose more [E43, E44, E45].

## Sources

> Checked 2026-11-09. Ids resolve in `references/memory/evidence-ledger.md`. The 90-day idle move and the archive retention are this package's choices, marked above.

| Claim | Source |
|---|---|
| Verify before acting; the repository wins | A29, A54, B68, F25 |
| Delta edits over whole-file rewrites | E40, E41 |
| Consolidation as merge, resolve, delete, re-fit | B38, B67, B74, D:C9 |
| Contradictions are resolved arbitrarily | A20 |
| Expiry and reinforcement | A53, D:C5, D:C12, F20 |
| No ablation behind published forgetting rules | E34, E35 |
| Three-granularity deletion and propagation | F35, F36, F37, F40, F43 |
| Append-only change log and snapshots | F15, F47 |
| Compaction loses in-context rules | E43, E44, E45 |
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 466kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 196kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 196kUpdated Claude CodeCodexVerifiedInstall