From 7b277732359ffa3413749f8b56861817595e5668 Mon Sep 17 00:00:00 2001 From: Pieter Viljoen Date: Fri, 31 Jul 2026 20:39:10 -0700 Subject: [PATCH 1/2] State the purpose as agent enablement, not orchestration The tagline described the repo by its contents: governance, orchestration and workflow audit. That names the machinery and not what the machinery is for, so a reader learns what is in here without learning why any of it exists. The purpose is agent enablement. An agent is fast and inconsistent, so a fleet built by one drifts a different way in every repository, and the drift stays invisible until something breaks where it matters. What this repo makes repeatable is the outcome, so an agent stands a repository up, changes it and releases it on its own, and lands in the same known-good shape every time. Framing the rules as guardrails rather than governance also states their direction correctly. They exist to widen what an agent may do unattended, by removing a decision it would otherwise make differently every time or by making a failure loud that would otherwise pass green. Write safety, the review loop and the audit are what make the autonomy safe to grant, and autonomy extends exactly as far as the verification reaches. The third paragraph records that none of it is finished. Every rule traces to a specific failure, nearly all observed in this fleet rather than imagined, and a procedure that lets a new one through is corrected as part of the work that found it. The same sentence opens README.md, HISTORY.md and AGENTS.md, so all three move together. The GitHub About description is derived from the README line and is updated after this merges. Co-Authored-By: Claude Opus 5 (1M context) --- AGENTS.md | 2 +- HISTORY.md | 2 +- README.md | 12 +++++++++--- 3 files changed, 11 insertions(+), 5 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index c76e8b94..e0eb0c29 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -1,6 +1,6 @@ # Instructions for AI Coding Agents -**ProjectTemplate** is a governance, agent-orchestration, and workflow-audit repo for a fleet of related projects. It holds the portable rules those projects follow, a machine-readable ground-truth spec ([`spec/`](./spec/)), a registry of the projects ([`registry/repos.json`](./registry/repos.json)), and an audit-agent instruction set ([`AUDIT.md`](./AUDIT.md)). It ships no sample application code. +**ProjectTemplate** is the agent-enablement hub for a fleet of related projects. It exists so an agent can work across them autonomously and productively, at repeatable quality, inside guardrails that keep the autonomy from doing harm. It holds the portable rules those projects follow, a machine-readable ground-truth spec ([`spec/`](./spec/)), a registry of the projects ([`registry/repos.json`](./registry/repos.json)), and an audit-agent instruction set ([`AUDIT.md`](./AUDIT.md)). It ships no sample application code. This file is the entry point every coding agent reads first, and it holds only two things: the rules for managing context and delegation, which apply to every task, and a map of where every other rule lives. The rule text itself is in [`GOVERNANCE.md`](./GOVERNANCE.md), one section per topic. Code style lives in [`CODESTYLE.md`](./CODESTYLE.md) (a General section plus per-language sections for .NET and Python), and the CI/CD workflow contract in [`WORKFLOW.md`](./WORKFLOW.md). diff --git a/HISTORY.md b/HISTORY.md index 0645c803..4659e59f 100644 --- a/HISTORY.md +++ b/HISTORY.md @@ -1,6 +1,6 @@ # ProjectTemplate -Governance, agent-orchestration, and workflow-audit hub for a fleet of related repositories. +Agent enablement for a fleet of repositories: the guardrails that let AI coding agents work autonomously and productively, at repeatable quality, without causing harm. ## Release History diff --git a/README.md b/README.md index 365fa65a..11b9ad54 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # ProjectTemplate -Governance, agent-orchestration, and workflow-audit hub for a fleet of related repositories. +Agent enablement for a fleet of repositories: the guardrails that let AI coding agents work autonomously and productively, at repeatable quality, without causing harm. ## Build and Distribution @@ -24,7 +24,7 @@ Governance, agent-orchestration, and workflow-audit hub for a fleet of related r **Summary**: -- Governance, agent-orchestration, and workflow-audit hub for the fleet: shared rules, a machine-readable spec, a fleet registry, per-repo audit reports, and an audit-agent instruction set. Ships no application code. +- Agent enablement for the fleet: shared rules, a machine-readable spec, a fleet registry, per-repo audit reports, and an audit-agent instruction set, so an agent works autonomously inside guardrails that prove the result. Ships no application code. See [Release History][history] for the full history. @@ -47,7 +47,13 @@ See [Release History][history] for the full history. ## What This Repo Is -This repo is the single home for the shared rules the fleet follows, a machine-readable spec those rules are checked against, a registry of the projects, and an audit-agent instruction set. It ships no application code. Each project owns its own implementation and is **audited** against the ground truth here - to the letter (exact file, section, or config) or to intent (an equivalent outcome). +**The purpose is agent enablement.** An AI coding agent is fast and inconsistent, so a fleet built by one drifts a different way in every repository, and the drift stays invisible until something breaks where it matters. What this repo makes repeatable is the outcome: an agent stands a repository up, changes it, and releases it on its own, and lands in the same known-good shape every time. The guardrails are what make granting that autonomy sound rather than reckless. + +**Guardrails here enable rather than restrain.** A rule earns its place by removing a decision an agent would otherwise make differently every time, or by making a failure loud that would otherwise pass green. Write safety bounds what an agent can reach outside the project in front of it, the review loop closes before anything merges, and the audit proves the result instead of accepting the agent's report of it. Autonomy extends exactly as far as the verification reaches. + +**Nothing here is finished.** Every rule traces to a specific failure, nearly all of them observed in this fleet rather than imagined, and a procedure that lets a new one through is corrected as part of the work that found it. The ground truth improves by being used. + +This repo is the single home for those rules, a machine-readable spec they are checked against, a registry of the projects, and an audit-agent instruction set. It ships no application code. Each project owns its own implementation and is **audited** against the ground truth here, to the letter (exact file, section, or config) or to intent (an equivalent outcome). - **[AGENTS.md][agents]** - the agent entry point: context and delegation rules, plus the map from a task to the section that governs it. - **[GOVERNANCE.md][governance]** - cross-cutting rules for AI coding agents: git, branching, release model, doc style, the recurring-violation rules (comments, ASCII charset, US spelling, line endings), PR review etiquette, and workflow YAML conventions. From e14502cb034fc5eb4ed62922022b303d2a5dba67 Mon Sep 17 00:00:00 2001 From: Pieter Viljoen Date: Fri, 31 Jul 2026 20:43:43 -0700 Subject: [PATCH 2/2] Fit the tagline to the canonical short-description limit spec/readme-structure.md item 1 caps the one-line description at 100 characters, link-free and single-sentence, because it doubles as the GitHub About description and, for a repo publishing an image, the Docker Hub short description, where the cap is tightest. The audit checks the length. The sentence this branch introduced ran to 167 and would have failed its own readme-structure dimension. The short form keeps what has to survive compression, agent enablement and autonomy at repeatable quality inside guardrails, and drops the harm clause, which the second paragraph of What This Repo Is states at length. HISTORY.md carries the identical sentence, since the audit checks the two match. AGENTS.md now opens on the same noun phrase rather than a hyphenated adjective, so the tagline reads as one term across the three files. Co-Authored-By: Claude Opus 5 (1M context) --- AGENTS.md | 2 +- HISTORY.md | 2 +- README.md | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index e0eb0c29..13d20700 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -1,6 +1,6 @@ # Instructions for AI Coding Agents -**ProjectTemplate** is the agent-enablement hub for a fleet of related projects. It exists so an agent can work across them autonomously and productively, at repeatable quality, inside guardrails that keep the autonomy from doing harm. It holds the portable rules those projects follow, a machine-readable ground-truth spec ([`spec/`](./spec/)), a registry of the projects ([`registry/repos.json`](./registry/repos.json)), and an audit-agent instruction set ([`AUDIT.md`](./AUDIT.md)). It ships no sample application code. +**ProjectTemplate** exists for agent enablement across a fleet of related projects, so an agent works over all of them autonomously and productively, at repeatable quality, inside guardrails that keep the autonomy from doing harm. It holds the portable rules those projects follow, a machine-readable ground-truth spec ([`spec/`](./spec/)), a registry of the projects ([`registry/repos.json`](./registry/repos.json)), and an audit-agent instruction set ([`AUDIT.md`](./AUDIT.md)). It ships no sample application code. This file is the entry point every coding agent reads first, and it holds only two things: the rules for managing context and delegation, which apply to every task, and a map of where every other rule lives. The rule text itself is in [`GOVERNANCE.md`](./GOVERNANCE.md), one section per topic. Code style lives in [`CODESTYLE.md`](./CODESTYLE.md) (a General section plus per-language sections for .NET and Python), and the CI/CD workflow contract in [`WORKFLOW.md`](./WORKFLOW.md). diff --git a/HISTORY.md b/HISTORY.md index 4659e59f..e6bfe7fa 100644 --- a/HISTORY.md +++ b/HISTORY.md @@ -1,6 +1,6 @@ # ProjectTemplate -Agent enablement for a fleet of repositories: the guardrails that let AI coding agents work autonomously and productively, at repeatable quality, without causing harm. +Agent enablement for a fleet of repositories: autonomy and repeatable quality inside guardrails. ## Release History diff --git a/README.md b/README.md index 11b9ad54..f0bbb22e 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # ProjectTemplate -Agent enablement for a fleet of repositories: the guardrails that let AI coding agents work autonomously and productively, at repeatable quality, without causing harm. +Agent enablement for a fleet of repositories: autonomy and repeatable quality inside guardrails. ## Build and Distribution