agentmods.dev

hexgate: Skill for Claude Code

.claude/skills/write-adr/SKILL.md

write-adr is a skill for Claude Code from HexamindOrganisation/hexgate. It costs 78 tokens per session (1,107 once invoked), scanned A, original, MIT.

A tool for writing Architecture Decision Records, or ADRs: files that preserve important technical decisions and the reasons behind them. It follows the repository's existing format and numbering rules.

In plain words
What is it for?
Use it to create or update one decision record in docs/adr/, including its status, affected files, required rules, and detailed reasoning.
Why use it?
It removes the risk of durable design or security decisions being recorded inconsistently or losing their rationale over time. It also handles marking older decisions as superseded.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is HexamindOrganisation/hexgate's own configuration. It tells Claude Code how to work on hexgate itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hexgate configures →

not rated 23repo changed 6d ago A scan 78 tokens original MIT
View source ↗ HexamindOrganisation/hexgate hexgate.ai
Reuse

Borrowing it

Nothing to install: this file belongs to HexamindOrganisation/hexgate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/HexamindOrganisation/hexgate/main/.claude/skills/write-adr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/HexamindOrganisation/hexgate

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.

agentmods badge for write-adr

README.md
[![agentmods](https://agentmods.dev/badge/skills/hexamindorganisation/hexgate/write-adr/github.svg)](https://agentmods.dev/skills/hexamindorganisation/hexgate/write-adr)
Your own site
<a href="https://agentmods.dev/skills/hexamindorganisation/hexgate/write-adr"><img src="https://agentmods.dev/badge/skills/hexamindorganisation/hexgate/write-adr/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.

agentmods 80×15 button for write-adr

Your own site · 80×15
<a href="https://agentmods.dev/skills/hexamindorganisation/hexgate/write-adr"><img src="https://agentmods.dev/badge/skills/hexamindorganisation/hexgate/write-adr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,107 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.01107
Opus 5.5 $0.00031 $0.00443
Sonnet 5.5 $0.00016 $0.00221
Haiku 4.5 $0.00008 $0.00111

Measured 6d ago against content hash 298528379db4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-adr 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 6d 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.

.claude/skills/write-adr/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write a hexgate ADR

ADRs live in docs/adr/, one decision per file, named R-<AREA>-<NNN>-<kebab-summary>.md (e.g. R-GUARD-002-guards-fail-closed.md). Read a couple of existing records first — they are the source of truth for the house style — then match them.

Terse on what, detailed on why. An agent reads these under a token budget and acts on them literally, so the decision must be unambiguous and the rationale must survive: six months later nobody remembers why, and without it someone "cleans up" the decision and reintroduces the bug it was avoiding. The rationale is the one part you must never compress.

Before writing

  • Pick the area and the next id. Existing areas: AGENT, AUTH, GUARD, POL, USAGE. Reuse one if the decision fits it; open a new area only for a genuinely new subsystem. Number is the next free integer in that area (ls docs/adr/).
  • One decision per file. If you can't state it in two sentences, it's probably two decisions — split it.
  • Superseding? Don't delete the old record. Set the old one's Status to Superseded by R-<AREA>-NNN (date) with a short "Why superseded" note, and set the new one's Status to supersedes …, so the chain resolves. See R-AGENT-001 → R-AGENT-002 for the pattern.

Required shape

Every record has these; keep the optional ones only when they earn their place.

  • Title — # R-<AREA>-NNN: <the decision as a short imperative phrase>.
  • Status — Accepted · <YYYY-MM-DD>, or Superseded by … / supersedes ….
  • Applies to — the exact file/dir globs the decision governs, e.g. `hexgate/guards/**`, `hexgate/adapters/**/tools.py`. This is what scopes the ADR: an agent loads it when touching those paths, so it is not always-on context. Be specific.
  • ## Decision — one or two imperative sentences, then MUST / MUST NOT bullets. Never "prefer" or "consider" — those let an agent do the opposite.
  • ## Why — the forces, the tradeoff, and what breaks if the rule is ignored. Spend words here. Name the concrete failure the decision avoids (an incident, a fail-open, a drift) if there is one.

Read the full file on GitHub · 98 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. 6d ago Changed 298528379db4
  2. 14d ago Changed ba00cb701ae8
  3. 1mo ago First seen · 98 lines · 78 tokens per session scan A e838454745c3

Subscribe to this mod's changes

write-adr is a skill published in the GitHub repository HexamindOrganisation/hexgate (23 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,107 once invoked, about $0.0003 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 2026-09-24.

PlanningWriting and docsagent-harnessaiai-agentsaudit-logauthorizationbiscuit-auth
Related

Other skills, from other repositories

theauth

Install and use theAuth (@glinr/theauth), the TypeScript auth SDK for AI agents and humans. Use when adding agent identity, scoped permissions, delegation, audit logs, human sign-in plugins, or an MCP OAuth 2.1 authorization server to a Node, Bun, Deno or edge project.

glincker/theauth · 67 tokens

agent-harness-fault-injection

Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.

sickn33/agentic-awesome-skills · 34 tokens

requirements-writer

Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.

mvschwarz/openrig · 28 tokens

refocusing

Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.

mvschwarz/openrig · 59 tokens

orchestration-team

Use when coordinating assignments, selected review boundaries, or blocked work across a rig.

mvschwarz/openrig · 21 tokens

oversight-team

Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…

mvschwarz/openrig · 117 tokens