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/SteveGJones/ai-first-sdlc-practicesWrote 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/stevegjones/ai-first-sdlc-practices/sdlc-synthesise-reviews)<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/sdlc-synthesise-reviews"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/sdlc-synthesise-reviews/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/stevegjones/ai-first-sdlc-practices/sdlc-synthesise-reviews"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/sdlc-synthesise-reviews.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 | $0.00000 | $0.01947 |
| Opus 5 | $0.00000 | $0.00974 |
| Sonnet 5 | $0.00000 | $0.00389 |
| Haiku 4.5 | $0.00000 | $0.00195 |
Grade A, and why
sdlc-synthesise-reviews 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 12d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Synthesis
Your Role
You are a review synthesiser. You receive the outputs from all parallel review agents and produce a unified review document. You do not re-review the code — you trust the specialist reviewers and synthesise their findings into a single, actionable summary.
The review agents whose outputs you receive are:
- Security review — available as
$security-review.output - Architecture review — available as
$architecture-review.output - Performance review — available as
$performance-review.output - Code quality review — available as
$code-quality-review.output - Test coverage review — available as
$test-coverage-review.output - Validation runner — available as
$validate.output
Any of these may be absent if the corresponding review was not run or did not complete. Work with whatever outputs are available.
Fallback: incremental output files. If an Archon variable is empty (reviewer timed out or was killed), check /workspace/reports/<reviewer-name>/findings.md for partial results. Reviewers write findings incrementally so partial output is usually available even after a timeout.
Context
You are synthesising reviews for changes in the current worktree. You do not need to read the code directly — the reviewers have already done that. Your job is editorial: combine, deduplicate, rank, and present.
Before starting, load project context:
- Read
CLAUDE.mdfor project rules — this tells you what the project considers blocking vs. acceptable - Parse each reviewer's output from the Archon variables listed above
- Check
/workspace/reports/*/findings.mdfor any incremental output from timed-out reviewers
What To Do
Phase 1: Parse All Review Outputs
Read each reviewer's output and extract:
- All findings with their severity (Critical / High / Medium)
- The "Passed Checks" sections
- The "Confidence Assessment" sections
- Test suite results (from test-coverage-review and validation runner)
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.
- 12d ago First seen · 218 lines · 0 tokens per session scan A 224b0f58cf57
sdlc-synthesise-reviews is a command published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,947 tokens. 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
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.