Gentle-AI configures an existing AI coding agent into an engineering environment with persistent memory, planning workflows, skills, tool servers, model routing, and optional review. Developers and teams use it to make coding agents follow project conventions and retain decisions across sessions. The catalogue entries are its skills, commands, agents, and instruction.
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/Gentleman-Programming/gentle-aiWrote 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/commands/gentleman-programming/gentle-ai/gentle-sdd-status)<a href="https://agentmods.dev/commands/gentleman-programming/gentle-ai/gentle-sdd-status"><img src="https://agentmods.dev/badge/commands/gentleman-programming/gentle-ai/gentle-sdd-status/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/commands/gentleman-programming/gentle-ai/gentle-sdd-status"><img src="https://agentmods.dev/badge/commands/gentleman-programming/gentle-ai/gentle-sdd-status.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 | $0.00009 | $0.00727 |
| Opus 5 | $0.00005 | $0.00364 |
| Sonnet 5 | $0.00002 | $0.00145 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
gentle-sdd-status 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 7d 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.
This is a copy
100% identical to sdd-status — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Show structured SDD status for an active change. This command is read-only: do not launch SDD executors and do not edit files.
HARD GATE:
SDD Session Preflight must already be complete for this session. It must include execution mode, artifact store, chained PR strategy, and review budget. If missing, ask the exact orchestrator preflight prompt and STOP. Do not inspect status in the same turn.
CONTEXT:
- Working directory: Detect agent-side before proceeding by running
git rev-parse --show-toplevelwith the Bash tool; if that fails, runpwdwith the Bash tool. - Current project: Derive agent-side from the detected working directory basename. Do not use slash-command shell interpolation for this value.
- Change name: $ARGUMENTS
TASK:
- If the
gentle-aibinary is available, rungentle-ai sdd-status [change] --cwd <repo> --json --instructionsand treat its JSON as authoritative — but only when the session artifact store isopenspecorhybrid. When the session artifact store isengram, do NOT invoke the native dispatcher at all — it cannot see the change (it reads onlyopenspec/changes/); resolve status entirely from Engram (mem_search+mem_get_observationon the change's topic keys) using the manual status schema in~/.claude/skills/_shared/sdd-status-contract.md(the same schema used when the binary is unavailable). The dispatcher is authoritative only foropenspec/hybrid. If unavailable, read~/.claude/skills/_shared/sdd-status-contract.mdand follow it. - Resolve the active change:
- If
$ARGUMENTSis provided, validate that exact change in the selected artifact store. - If omitted and exactly one active change exists, select it and say how it was selected.
- If omitted or ambiguous with multiple active changes, ask the user to choose and STOP. Do not guess.
- If
- Inspect the selected artifact store from session preflight. Do not hardcode Engram.
- Return structured status with:
- Active change selection and schemaName.
- planningHome, changeRoot, artifactPaths, and contextFiles.
- Artifact statuses for proposal, specs, design, tasks, apply-progress, and verify-report.
- Task progress: total, completed, pending, and allComplete.
- Dependency states for proposal, specs, design, tasks, apply, verify, and archive.
- Next recommended action.
- actionContext mode, workspace root, and allowed edit roots.
READ-ONLY RULES:
- Do not create, update, or delete artifacts.
- Do not mark tasks complete.
- Do not launch apply, verify, archive, or continue.
- Do not infer routing from free text. Use
nextRecommendedand dependency states. IfblockedReasonsis non-empty, do not proceed to apply, archive, or terminal work. IfnextRecommendedisverify, verification/remediation may run only to refresh evidence; ifnextRecommendedisresolve-blockers, reportblockedReasonsand stop; ifnextRecommendedis a planning token (propose,spec,design, ortasks), launch the corresponding planning phase. - If status cannot be resolved safely, return
status: blockedwith the missing information.
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.
- 7d ago First seen · 41 lines · 9 tokens per session scan A fdcfab9d3d97
gentle-sdd-status is a command published in the GitHub repository Gentleman-Programming/gentle-ai (6,475 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 727 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to sdd-status, differing in 9 lines, and is treated as a copy.
Other commands, from other repositories
pr-feedback-ingest
Turn PR feedback (Greptile, CI, bots, humans) into a structured traceable backlog aligned with TASKSTATE.md, DECISIONS.md, and IMPLEMENTATIONPLAN.md so the next execution step can be a narrow implement-approved-slice or a small planning touch without losing alignment. Corrective scope only. Use when a PR is open or…
post-review-pivot
Capture what a PR or team review changed about the intended behavior or approach, separate keep vs revert/replace, and produce the smallest safe set of updates to task memory and follow-on work. Does not implement product code. Use when a PR or team feedback requests a meaningful direction change (wrong fields, wrong…
arrange-workspace-flow-choose-workspace-layout
Phase 1 Choose Workspace Layout of arrange-workspace-flow.
arrange-workspace-flow
Workflow for arranging a workspace: layout, reference source code, business/technical context, ecosystem setup.
taskstoissues
A command that turns structured tasks from project design documents into ordered GitHub Issues, written in simplified Chinese.
cross-audit
Second-model review. Picks an auditor (codex/gemini/opencode/aider/copilot), excludes the caller, writes a prompt to paste, reads the response back. Usage: /cross-audit [--with | list | compare].