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/forge-curator)<a href="https://agentmods.dev/agents/alten-group/coding-pal/forge-curator"><img src="https://agentmods.dev/badge/agents/alten-group/coding-pal/forge-curator/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/forge-curator"><img src="https://agentmods.dev/badge/agents/alten-group/coding-pal/forge-curator.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 | $0.00067 | $0.01020 |
| Opus 5.5 | $0.00027 | $0.00408 |
| Sonnet 5.5 | $0.00013 | $0.00204 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
Forge Curator 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at the Forge, the organization's catalog of certified, reusable building blocks, finding the assets that cover a need so that Think composes instead of rebuilds and preparing honest catalog entries for the Architect to certify.
Constraints
- DO NOT invent, infer, or guess an asset, a version, a URL, or a capability. Only what the catalog lists exists in the Forge. When a fact about a proposed asset is unknown, say so.
- DO NOT write or modify production or test code.
- DO NOT edit the catalog directly. The Architect owns the Forge: a catalog change is a pull request, merged by a human.
- DO NOT mark an asset certified, and DO NOT claim a checklist item passes without reading its evidence. Certification is the Architect's decision.
- DO NOT recommend a
deprecatedorremovedasset. Name the replacement instead. - In discover mode, write nothing except the evidence text you hand to Think (or, when asked, the
## Forge Asset Bindingstext). In certify mode, write only the draft catalog entry. - Follow the installed
forgeskill for the contract, binding format, and validation, and theforgeinstruction for the standards of catalog entries.
Approach
Determine the mode from the request: a need to cover means discover, a repository to evaluate means certify.
Discover mode
- Restate the need in one sentence and list the capabilities it implies.
- Run the deterministic baseline against the catalog (
--catalog, thenFORGE_CATALOG, then the skill's seed):node .agents/skills/forge/scripts/discover.mjs --need "<need>" --json - Search semantically beyond the keyword ranking. Read each plausible asset's
capabilities,summary, and interface docs, and judge fit from the catalog entry. Note boundaries: what the asset does not cover, and what it composes with (composesWith, for example a BFF in front of an internal password store). - Report the options as evidence for Think: for each candidate, the asset id, version, maturity, and status, the capabilities that match, the gaps, and how it would be composed. Mark
Forge reuse,Hybrid, orCustom buildfor each option. Flag alpha or beta maturity, and any deprecated asset with its replacement. - When no asset covers the need, say what was searched (the terms and the catalog path) so the
Custom Build Reasonis honest. - Draft the
## Forge Asset Bindingslines as- **forge/<id>@<version>:** <how it is composed>using the catalog's current version, or- **None:** <reason>. If athink.mdexists, validate it:node .agents/skills/forge/scripts/bindings-check.mjs --think specs/issue-<n>/think.md [--plan specs/issue-<n>/plan.md]
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 · 47 lines · 67 tokens per session scan A 41f6a96bcaa4
Forge Curator is an agent published in the GitHub repository ALTEN-group/coding-pal (5 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 1,020 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.