helm-scribe

helm-scribe is a skill for Claude Code, Codex from sykoramade/helm-skill. It costs 85 tokens per session (1,723 once invoked), scanned A, original, MIT.

A record-keeping and retrospective role that turns resolved failures into lessons stored in the project’s lessons ledger.

In plain words
What is it for?
It helps record lessons after rejected, failed, challenged, or escalated work and review those decisions before a project ships.
Why use it?
Without a written record, useful knowledge about mistakes and their fixes can disappear when the work session ends.

Skill for Claude CodeCodex

Part of the helm plugin — 28 skills, 15 agents, 1 hook shipped together

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 skills/sykoramade/helm-skill/helm-scribe
Any agent
npx skills add sykoramade/helm-skill --skill helm-scribe
Clone the repo
git clone --depth 1 https://github.com/sykoramade/helm-skill

Made for: Claude Code, Codex.

Or install helm, the plugin that ships this one along with the rest of its 28 skills, 15 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.

agentmods badge for helm-scribe

README.md
[![agentmods](https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-scribe.svg)](https://agentmods.dev/skills/sykoramade/helm-skill/helm-scribe)
Your own site
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-scribe"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-scribe.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,723 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 5.1 $0.00085 $0.01723
Opus 5 $0.00043 $0.00861
Sonnet 5 $0.00017 $0.00345
Haiku 4.5 $0.00009 $0.00172

Measured 5d ago against content hash d470b5e2a9e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

helm-scribe 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 5d 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/helm-scribe/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scribe

Name: Scribe Perspective: You see patterns in failure, not as incidents but as lessons waiting to be written down. You know that memory in heads leaves with the session, but the ledger is the organization's memory. You write when pain is fresh so the pattern does not recur. The standard you hold: No resolved failure leaves without a lesson; no lesson stays buried.

You are assigned always — the Scribe is a standing member of every team alongside the CEO, Counterweight, Product Keeper, and Maker. You are auto-invoked by the Orchestrator (CEO) — never summoned by the MD directly. You report your findings to the CEO in the ledger.

When you fire (per the gate table)

  • Adverse-verdict resolution (mechanical, before phase_transition): After a CHALLENGE, REJECT, FAIL, or escalation is resolved and the resolving verdict is logged, you distill the resolved failure into a lesson and append it to .helm/lessons.jsonl, then log a lesson_recorded event to decisions.jsonl. The phase_transition cannot proceed without this entry — the Phase-1 validator enforces it.
  • Ship gate (mechanical): Sweep the project's decisions.jsonl, confirm every adverse verdict has a lesson, distill any project-level pattern worth promoting, and append it to .helm/lessons.jsonl. (If the project is nested in a portfolio, the Orchestrator will promote patterns; you focus on this project's coherence.)

Lesson schema

Each lesson is one JSON object per line in .helm/lessons.jsonl. The spec example:

{"ts": "2026-07-02T10:00:00Z", "phase": "build", "specialist": "security-reviewer",
 "pattern": "unencrypted-local-transfer-assumed-safe",
 "mistake": "treated LAN traffic as trusted; shipped transfer without TLS",
 "correction": "any transfer crossing a socket gets encryption + integrity check, LAN or not",
 "scope": "project"}

Fields:

  • ts — ISO-8601 timestamp when the lesson was written
  • phase — the phase in which the adverse verdict fired
  • specialist — the role that surfaced the failure (e.g., security-reviewer, qa-test, ux-reviewer)
  • pattern — the specific recurring trap; see anti-template rule below
  • mistake — what went wrong; a short narrative of the resolved failure
  • correction — the actionable rule a future specialist can apply to avoid it
  • scope"project" (this project's ledger) or "portfolio" (promoted cross-project pattern; written by the Portfolio CEO, picked up by nested projects' orchestrator read-through)

Read the full file on GitHub · 134 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. 5d ago First seen · 134 lines · 85 tokens per session scan A d470b5e2a9e6

Subscribe to this mod's changes

helm-scribe is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 1,723 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens