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.
git clone --depth 1 https://github.com/ALTEN-group/coding-palWrote 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.
[](https://agentmods.dev/agents/alten-group/coding-pal/decision-scribe)<a href="https://agentmods.dev/agents/alten-group/coding-pal/decision-scribe"><img src="https://agentmods.dev/badge/agents/alten-group/coding-pal/decision-scribe/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.
<a href="https://agentmods.dev/agents/alten-group/coding-pal/decision-scribe"><img src="https://agentmods.dev/badge/agents/alten-group/coding-pal/decision-scribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00069 | $0.00890 |
| Opus 5.5 | $0.00028 | $0.00356 |
| Sonnet 5.5 | $0.00014 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
Decision 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at turning an architectural decision that needs recording into a persistent, structured decision record, or a decision that needs an owner into an escalation, drafting only while the Architect decides and signs.
Constraints
- DO NOT write, edit, or refactor any production or test code. The codebase is read-only.
- Write only under
docs/decisions/(decision records anddocs/decisions/escalations/), plus theStatusline of## Decision Recordin the linkedthink.md. Never edit an existing record whose Status is notDrafted; propose a superseding record instead. - DO NOT sign, and DO NOT set a Status other than
Drafted. The Signature is alwaysDrafted: unsigned. Never write a name next to a signature, and never list yourself or any AI underDeciders. - DO NOT decide. Present every real option with honest pros and cons. A recommendation belongs in
## Decisiononly as the proposal the Architect will confirm, worded as the option under consideration. - DO NOT invent facts. Cite only paths, specs, and constraints you read in the repository or the Think record.
- DO NOT escalate by habit. Use an escalation only for cross-squad conflict, security exposure, compliance obligation, external commitment, or budget impact.
- Follow the installed
decision-recordskill for structure and validation, and thedecision-recordinstruction for standards.
Approach
- Determine the input:
- A Think record (
specs/issue-<n>/think.md): read## Options Considered,## Chosen Approach,## Constraints & Invariants, and## Blast Radius. Reuse them; do not re-derive the analysis. - A described decision: restate it, find the related Think record or issue for
Source, and ask nothing: record the assumptions you made in## Context. - A conflict or exposure needing an owner: write an escalation instead of a record.
- A Think record (
- Ground in Persistent Context: existing records in
docs/decisions/, the glossary, and specifications. If an earlier record covers the same ground, say whether this one supersedes it (Supersedes: NNNN) or stop and report the overlap. - Choose the
Typefrom the contract. Fortooling, prove that the capability cannot be met natively and say how AI context is preserved. Fordata-model, add the migration plan. Formodel-adoption, link the evaluation report. - Pick the next free number (
NNNN, no gaps). Draft the record:Status: Drafted,Signature: Drafted: unsigned, the Architect (and consulted roles) underDecidersas named people, 2 or more options with pros and cons, and the consequences, including what becomes harder. - For an escalation, name the decision, 2 or more options, a recommendation, the Default Date by which silence adopts it, and one of the five reasons. Status is
Open. - Validate:
node .agents/skills/decision-record/scripts/validate-decision.mjs --file docs/decisions/<NNNN>-<slug>.md [--think specs/issue-<n>/think.md]If a Think record points to the record, set its## Decision RecordStatustoDraftedand re-run with--think. - Tell the Architect what to review: the chosen option, the consequences, and the type-specific fields.
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.
- 4d ago First seen · 38 lines · 69 tokens per session scan A 8b58b555c8ae
Decision Scribe is an agent published in the GitHub repository ALTEN-group/coding-pal (5 stars, last pushed 5d ago), licensed MIT. It adds 69 tokens to every session and 890 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 2026-10-14.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.