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.
npx agentmods add commands/gentleman-programming/gentle-ai/sdd-archivegit 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/sdd-archive)<a href="https://agentmods.dev/commands/gentleman-programming/gentle-ai/sdd-archive"><img src="https://agentmods.dev/badge/commands/gentleman-programming/gentle-ai/sdd-archive.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00918 |
| Opus 5 | $0.00007 | $0.00459 |
| Sonnet 5 | $0.00003 | $0.00184 |
| Haiku 4.5 | $0.00001 | $0.00092 |
Grade A, and why
sdd-archive 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- gentle-sdd-archive — 100% identical, 56 lines differ
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the gentle-orchestrator, not an SDD executor. This command may launch the hidden sdd-archive sub-agent only after the orchestration gates below pass.
CONTEXT:
- Working directory: before doing anything else, run
git rev-parse --show-toplevel 2>/dev/null || pwdwith your bash tool and use the returned path as the authoritative workspace. In OpenCode Desktop (Electron) the parse-time interpolation resolves to the app data directory, not the project. - Current project: the
basenameof the detected workspace above.
HARD GATES:
- 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 run archive in the same turn.
sdd-initmust already exist or be run after preflight, per the orchestrator init guard.- Resolve the active change using the status contract. If
$ARGUMENTSis missing or ambiguous, ask the user to choose and STOP. Do not guess. - Produce structured status before acting. Use the resolved artifact store from session preflight; do not hardcode Engram. Archive only when refreshed native SDD status reports
dependencies.archive: readyandnextRecommended: archive. - The active change must have tasks and verify-report at the exact selected-store references.
reviewOfferis optional and never an archive or delivery gate. Archive reads only task completion and independent verification; a review offer may be declined or completed without changing archive readiness. Proposal/spec/design are expected for full spec-driven archive; if missing, report the exact missing artifacts and require an explicit user override before archiving. - actionContext must allow archive operations. If status reports
workspace-planning, STOP and explain that workspace archive is not supported in this slice. - The persisted tasks artifact must reflect completion before the archive is considered successful. Internal todos do not count, and
sdd-applyis responsible for marking completed tasks.
DEPENDENCY CHECK:
- If the verification report is missing or does not say the change is ready, do NOT archive.
- If tasks still contains unchecked implementation items (
- [ ]), do NOT archive by default. Send the change back tosdd-applyto correct the persisted tasks artifact. Only allow archive-time mechanical reconciliation when apply-progress / verify-report prove every unchecked task is complete; record the reconciliation in the archive report. - If verify-report contains CRITICAL issues, do NOT archive. There is no CRITICAL override.
- Tell the user what is missing and suggest
/sdd-verify <change>or/sdd-continue <change>.
TASK:
If all gates pass, launch the hidden sdd-archive sub-agent with the structured status, required artifacts, the resolved artifact store, and any explicit non-critical partial-archive or stale-checkbox reconciliation text. Enforce task completion and verification evidence only; review does not supply an archive gate or durable approval artifact. Treat checkbox fixes as exceptional reconciliation rather than normal archive work. For openspec or hybrid stores only, mandate mechanical filesystem copy/move (cp -R/mv/git mv via the shell) for every filesystem artifact — NEVER model Read/Write copying, which can truncate bytes silently — and require a diff -r readback (source vs. destination, archive-report additive-only) whose verbatim output appears in the result; an empty diff is the only passing evidence and a skipped diff -r FAILS the phase. For engram, do not perform filesystem synchronization or archive moves; retrieve the required Engram artifacts and persist the final archive report to sdd/{change-name}/archive-report. For none, do not perform filesystem operations or Engram persistence; return the closure summary only. Forward explicit final-state facts for any work completed after apply-progress or verify-report were persisted (fixed warnings, resolved blockers, updated counts); those artifacts are intermediate snapshots, and explicit final-state facts in the launch prompt outrank stale snapshot claims.
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 Changed · -12 lines 4a178f8513dd
- 6d ago First seen · 47 lines · 14 tokens per session scan A 77849cc250dc
sdd-archive is a command published in the GitHub repository Gentleman-Programming/gentle-ai (6,301 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 918 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
cross-critique
Adversarial multi-angle critique. All three auditors fire in parallel (codex=technical, gemini=strategic, claude=ux). Counter-args ranked by rebuttal survival score, not raw severity. Usage: /cross-critique [--with | list | compare].
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].
make
Refresh, reconfigure, or extend the project's harness at /.claude/. Asks the user what they want to do before invoking the CLI.
repo-consistency-sweep
Proactive defect-class detection that handles the lower-value half of code review (per Bacchelli and Bird 2013) so human reviewers stay focused on design, intent, and knowledge transfer. Catches convention drift, ordering bugs, type-safety gaps, security and multi-tenant invariants (CWE-grounded), and operability…
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…
code-review
Run parallel specialized review agents and produce aggregated quality report.