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/assured-bundle-review)<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/assured-bundle-review"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/assured-bundle-review/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/assured-bundle-review"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/assured-bundle-review.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 | $0.01288 |
| Opus 5 | $0.00000 | $0.00644 |
| Sonnet 5 | $0.00000 | $0.00258 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
assured-bundle-review 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 10d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assured Bundle Review
Your Role
You are a senior solution architect reviewing the Assured bundle (plugins/sdlc-assured/) — the Method 2 regulated-industry substrate from EPIC #178 Phase E. This bundle layers on the Phase D Programme substrate. Phase F (real dogfood) layers on this; getting Assured right matters.
You operate in a fresh container with SDLC plugins installed. Use the sdlc-team-common:solution-architect agent (via the Agent tool with subagent_type="sdlc-team-common:solution-architect") for the architectural review.
What you're reviewing
Primary input: plugins/sdlc-assured/ (the entire bundle).
Walk these files specifically:
plugins/sdlc-assured/manifest.yamlplugins/sdlc-assured/CONSTITUTION.md— Articles 15-17plugins/sdlc-assured/templates/{programs.yaml, visibility-rules.md, change-impact.md, requirements-spec-assured.md, design-spec-assured.md, test-spec-assured.md}plugins/sdlc-assured/scripts/assured/{ids.py, traceability_validators.py, decomposition.py, code_index.py, render.py, export.py}plugins/sdlc-assured/skills/*/SKILL.md— 8 skillsplugins/sdlc-assured/README.md
Required context
docs/architecture/option-bundle-contract.md— bundle contract (Phase C)docs/superpowers/specs/2026-04-26-programme-assured-bundles-design.md§4 — Method 2 designresearch/sdlc-bundles/METHODS.md§4 — Method 2 summarytests/fixtures/assured/feature-sample/— minimal feature fixturetests/test_assured_*.py— unit and integration tests- The Phase D containerised review at
research/sdlc-bundles/dogfood-workflows/programme-bundle-review-output.mdfor review-style precedent
What to do
Dispatch the sdlc-team-common:solution-architect agent with the prompt below.
Prompt to dispatch
You are conducting an INDEPENDENT critical review of the Assured bundle
at plugins/sdlc-assured/ — Phase E deliverable of EPIC #178.
Phase F (real dogfood on EPIC #142) layers on this substrate; getting
Assured right matters.
Required reading first:
- docs/architecture/option-bundle-contract.md (Phase C contract)
- docs/superpowers/specs/2026-04-26-programme-assured-bundles-design.md §4 (Method 2 design)
- research/sdlc-bundles/METHODS.md §4
- plugins/sdlc-assured/ (the bundle itself)
- tests/test_assured_*.py
You may walk plugins/sdlc-programme/, plugins/sdlc-knowledge-base/,
plugins/sdlc-core/ to compare conventions.
Answer these 6 questions, in order, each with a verdict (AGREE /
AGREE-WITH-CONCERNS / DISAGREE / NEEDS-REWORK):
1. **Constitution overlay soundness (Articles 15-17)**: do the new
articles extend articles 1-14 cleanly? Are there gaps between what
the constitution promises and what the validators actually
enforce?
2. **ID system fitness**: does the positional namespace ID format
(`P1.SP2.M3.REQ-007`) coexist cleanly with the flat form
(`REQ-feature-NNN`)? Does `remap_ids` actually preserve traceability
under decomposition refactoring? What edge cases worry you?
3. **Traceability validator coverage**: do the 4 mandatory + 1 optional
validators catch the broken-reference cases regulated-industry
teams care about? Specifically: forward link integrity (DES with
no satisfies, TEST with no satisfies), backward coverage (REQ
with no DES, DES with no TEST), idempotency, annotation format.
4. **Decomposition validator coverage**: do the 5 module-bound
validators correctly model DDD bounded contexts + Bazel
visibility-rule discipline? Specifically: anaemic-context
detection (does the implementation actually catch scattered
logic?), granularity match (warns vs blocks correctly?),
visibility rule advisory vs strict.
5. **KB integration realism**: does the `SYNTHESISE-ACROSS-SPEC-TYPES`
mode actually compose with the existing `synthesis-librarian`
without breaking the existing modes? Does the `_code-index.md`
shelf-shape match what the `research-librarian` queries?
6. **Bundle layout vs Phase C contract**: does the actual Assured
bundle layout match what docs/architecture/option-bundle-contract.md
specifies? Are reserved Phase E fields (decomposition_support,
id_format, paths_split_supported, known_violations_field,
anaemic_context_opt_out) used correctly?
Then provide a SUMMARY paragraph stating whether the Assured bundle is
good enough to ship as v0.1.0 AND whether Phase F (real dogfood) can
proceed without retrofit, or whether Phase E needs revision before
either.
End your review by writing the verbatim review (6 verdicts + summary) to:
research/sdlc-bundles/dogfood-workflows/assured-bundle-review-output.md
Do NOT propose alternative bundles. Do NOT modify the bundle. Do NOT
dispatch other agents. Read-only review; output is a markdown file.
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.
- 10d ago First seen · 109 lines · 0 tokens per session scan A 3bb475d4cacf
assured-bundle-review 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 1,288 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.