8000 README, brand kit and repo front page for aloop by adeelahmad · Pull Request #88 · adeelahmad/aloop · GitHub
[go: up one dir, main page]

Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions .claude-plugin/marketplace.json
Original file line number Diff line number Diff line change
@@ -1,16 +1,16 @@
{
"name": "aloop-marketplace",
"owner": { "name": "Adeel Ahmad" },
"description": "Agentic agile planning + autonomous TDD execution for Claude Code, Codex and OpenCode, with deterministic hook gates.",
"description": "Aladdin's Loop: one line of intent becomes planned, test-first, gate-verified code on Claude Code, Codex and OpenCode. Models explore; gates decide.",
"plugins": [
{
"name": "aloop",
"source": "./plugin",
"displayName": "Aladdin (aloop)",
"description": "Two-stage planning + two-phase TDD execution with deterministic hook gates, per-task transcripts, and a memory-producing retrospective.",
"author": { "name": "Adeel Ahmad" },
"homepage": "https://github.com/adeelahmad/agentic-agile",
"repository": "https://github.com/adeelahmad/agentic-agile",
"homepage": "https://github.com/adeelahmad/aloop",
"repository": "https://github.com/adeelahmad/aloop",
"license": "MIT",
"category": "development",
"keywords": ["agile","tdd","orchestration","hooks","sub-agents","worktrees","determinism","gates","retrospective","memory"],
Expand Down
7 changes: 4 additions & 3 deletions .githooks/pre-push
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
#!/usr/bin/env bash
# pre-push — the full local gate before publishing. Installed by `make hooks`.
# Runs everything CI runs (`make ci`): fmt-check, lint (clippy · shellcheck · json),
# test (ctx-symbols + md-db), and eval-suite validation. shellcheck self-skips with
# Runs `make ci` (CI's offline checks except version-check): fmt-check, lint (clippy · shellcheck · pycheck · json),
# test (ctx-symbols + md-db), eval-suite validation, the host suites (test-hosts) and
# the conformance fixtures. shellcheck self-skips with
# a warning if it is not installed; CI enforces it.
set -euo pipefail

Expand All @@ -16,5 +17,5 @@ cd "$(git rev-parse --show-toplevel)"

command -v make >/dev/null 2>&1 || { echo "pre-push: make not found; skipping"; exit 0; }

echo "pre-push: make ci (fmt-check · lint · test · eval-validate)"
echo "pre-push: make ci (fmt-check · lint · test · eval-validate · test-hosts · conformance)"
make ci
39 changes: 39 additions & 0 deletions .github/ISSUE_TEMPLATE/bug.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
name: Bug report
description: A gate blocked something it should not have, let through something it should have blocked, or a tool misbehaved.
labels: [bug]
body:
- type: textarea
id: what
attributes:
label: What happened
description: What you ran, what you expected, and what happened instead.
validations:
required: true
- type: textarea
id: repro
attributes:
label: How to reproduce
description: The smallest steps, ideally a failing `scripts/test/*.test.py` case or the gate's BLOCK line.
render: shell
validations:
required: true
- type: dropdown
id: host
attributes:
label: Host
options: [Claude Code, Codex, OpenCode, Other]
validations:
required: true
- type: input
id: version
attributes:
label: aloop version
description: "The plugin version shown in `/plugin`, or `version` in `plugin/.claude-plugin/plugin.json`"
validations:
required: true
- type: textarea
id: logs
attributes:
label: Gate log
description: The relevant lines of `.aladdin/logs/gates.jsonl` (or `.agentic/logs/gates.jsonl`).
render: json
8 changes: 8 additions & 0 deletions .github/ISSUE_TEMPLATE/config.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
blank_issues_enabled: false
contact_links:
- name: What aloop is
url: https://github.com/adeelahmad/aloop/blob/master/docs/OVERVIEW.md
about: Read the overview before asking; it is written from the code.
- name: Security vulnerability
url: https://github.com/adeelahmad/aloop/blob/master/SECURITY.md
about: Report privately, never in a public issue.
25 changes: 25 additions & 0 deletions .github/ISSUE_TEMPLATE/feature.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
name: Feature request
description: Propose a gate, a host, a language or a mission-layer change.
labels: [enhancement]
body:
- type: textarea
id: problem
attributes:
label: The problem
description: What goes wrong today, or what you cannot do. Evidence (a live run, a gate log) helps most.
validations:
required: true
- type: textarea
id: proposal
attributes:
label: The proposal
description: What should change, and which deterministic check would prove it works.
validations:
required: true
- type: dropdown
id: area
attributes:
label: Area
options: [Gates, Planning, Execution, Hosts, Mission layer, Audit and stats, Docs, Other]
validations:
required: true
8 changes: 5 additions & 3 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ tag in lockstep. Tag releases as `vMAJOR.MINOR.PATCH`.
## [Unreleased]

### Added
- Brand kit and repo front page: `docs/brand/` holds the mark (an **a** whose bowl is a red-to-green loop passing a gold gate, with a 16 px cut), lockups, light and dark README banners, favicons, app icons, the site's OG card and the GitHub social preview, all generated by `docs/brand/gen_brand.py` from one palette with WCAG checks (rules in `docs/brand/README.md`). The README leads with the mission layer, the agent principles and the door rule, the supported hosts and the measured demo runs; the site carries the favicon and Open Graph/Twitter card metadata; `SECURITY.md` and bug/feature issue forms are new.
- The mission layer's six fixed roles (ROADMAP §4.12, M9.9): `market-researcher`, `product-tester`, `state-assessor`, `evaluator`, `mission-planner` and `ethics-reviewer`, each a persona with a four-case eval suite, a model route (the four that judge on the planning route, the two that measure on the worker route), hook matchers on Claude Code, Codex and OpenCode, and Codex/OpenCode agents from `aloop install` (which also renders the mission skill for OpenCode as `aloop-mission` once it ships). `plugin/mission/roles.json` names the paths each role writes. `gate-mission-scope` (PreToolUse) is the role path guard: a mission role never writes source, mission.json or another role's dir, never commits and never runs a human's approval; a builder never writes `docs/agents/mission/` or runs a writing `mission` command; the supervisor never hand-writes a role's artifact. No one hand-writes `docs/agents/mission/ledger.jsonl` or the captured prompts a grant reads (`<run data>/transcripts/`), runs a hook's `transcripts prompt|record|…`, or starts a host session from a tool call where a mission is set (its prompt would count as the human's words, M9.17), and no dispatched agent runs `mission baseline restore`, `events authority` or an `events emit` of a human event. `gate-mission-artifact` records what exists when a role starts and, at its stop, requires an artifact in its own paths that passes the core contract and its area's check, refuses a deleted artifact, a change to another role's or a ledger that no longer verifies, and records `artifact.created|updated` as provenance. A mission write never arms the sprint lock. The scope gate reads a Bash command as the shell would (`_shellread.py`: quotes, comments, line continuations, heredocs, wrappers such as `timeout` and `env`, `bash -c`, `eval`, a script run by an interpreter, variables and `$(mktemp)`). Each area's check runs once per artifact with its id or subject, an ethics hard line is the reviewer's finding, not a defect, and a derived goal whose only blocks are its pending ethics review waits on the Ethics Reviewer, not on the planner. Test: `mission-roles.test.py` (32 checks, with each role run through the real journeys, baseline, assess, evaluate and ethics, goal, research and judge areas), `mission-scope-bash.test.py` (220 commands), `opencode-plugin.test.mjs`.
- Mission approvals are the human's own words (ROADMAP §4.12, M9.17): `mission approve`, `baseline confirm|restore`, `journeys approve`, `mission ethics consent` and `mission telemetry consent` record only when a prompt the `UserPromptSubmit` hook captured has a line such as `approve msn_… 3f2a9c1b` (the verb and the first 8 hex of the content's sha256); until then they ask (exit 3) with that line. `--by` alone, a negated line, another code, a line older than a later decision about the subject (for a baseline, any version's confirmation) and a hand-appended ledger row without such a line grant nothing. Reason: an approval was only as strong as `--by`, so a role could approve its own mission change. Tests: `mission-core.test.py`, `mission-baseline.test.py`.
- Mission goals and the Aladdin handoff (ROADMAP §4.12, M9.11): `aloop mission goal derive` turns the Evaluator's gaps (in its own priority order) into a goal (autonomous: the top N; spoon-fed: the gaps the human picks with `--pick … --by`, which is the goal's approval) that names its targets and is bound to the mission's content, the eval, the principles block for the mission's mode and the Aladdin autonomy it maps to; `goal check` holds every intent until the goal is the content `derive` recorded, the mission is unchanged and approved and the mission's and the goal's ethics pass; `goal intents` writes one Intent Contract per gap (`intent new --source mission --goal --gap`, filled without a model, and refused for a goal that fails its check); `goal next` normalizes them one sprint at a time; `goal close` marks an active goal met once an evaluation of it says so; goals come only from the latest recorded evaluation, whose state `mission assess` measured, and `events emit` can no longer forge the state, eval or intent records; a gap a hard line fixed is held out of every later goal; `events trace` walks a commit back through intent → goal → eval → ethics → mission → its approver. Test: `mission-goal.test.py`.
Expand Down Expand Up @@ -128,6 +129,7 @@ tag in lockstep. Tag releases as `vMAJOR.MINOR.PATCH`.
`0`, so the scaffold gate's block text broke mid-sentence on CI-like hosts; it prints one number.

### Changed
- Links, manifests (`homepage`, `repository`), the installer's printed next steps and the site point at `adeelahmad/aloop` (the old `agentic-agile` URL redirects). The workflow diagram, OVERVIEW and plugin README use the current names and run-data path (`.aladdin/`); OVERVIEW's north-star numbers now come from the evidence ledger; the Rust minimum is 1.85 everywhere.
- The supervisor's playbook is 16% shorter: the sections a normal run does not need (Codex/OpenCode notes, the budget re-plan route and breach classes, review blind spots, the script list, transcripts, worktree hygiene) moved to `skills/aloop/reference.md`, read on demand from one-line pointers; OpenCode installs copy it beside the skill. Reason: SKILL.md is re-read on every supervisor turn (run 26: 6k fewer tokens per turn). Test: `aladdin-cli.test.py`.
- SKILL.md: a RED mandate names `tests/common/mod.rs` as the shims' home, never a `src/` path
(one `gate-red-verify` block per live run 14–18 came from a mandate saying "shim in `src/lib.rs`").
Expand Down Expand Up @@ -986,6 +988,6 @@ Initial release.
should be smoke-tested in a real Claude Code session.
- Suppression detection is syntactic (see SKILL.md "Known gate limitations").

[Unreleased]: https://github.com/adeelahmad/agentic-agile/compare/v0.12.0...HEAD
[0.12.0]: https://github.com/adeelahmad/agentic-agile/compare/v0.11.0...v0.12.0
[0.1.0]: https://github.com/adeelahmad/agentic-agile/releases/tag/v0.1.0
[Unreleased]: https://github.com/adeelahmad/aloop/compare/v0.12.0...HEAD
[0.12.0]: https://github.com/adeelahmad/aloop/compare/v0.11.0...v0.12.0
[0.1.0]: https://github.com/adeelahmad/aloop/releases/tag/v0.1.0
Loading
Loading
0