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 skills add tomzx/agents --skill backpropagate-sdlcgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/skills/tomzx/agents/backpropagate-sdlc)<a href="https://agentmods.dev/skills/tomzx/agents/backpropagate-sdlc"><img src="https://agentmods.dev/badge/skills/tomzx/agents/backpropagate-sdlc/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/skills/tomzx/agents/backpropagate-sdlc"><img src="https://agentmods.dev/badge/skills/tomzx/agents/backpropagate-sdlc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.04723 |
| Opus 5.5 | $0.00028 | $0.01889 |
| Sonnet 5.5 | $0.00014 | $0.00945 |
| Haiku 4.5 | $0.00007 | $0.00472 |
Grade A, and why
backpropagate-sdlc 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 2mo 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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backpropagate SDLC
Walks the SDLC artifact chain in reverse, from the shipped code back to the originating issue, verifying that every layer stays consistent with what was actually built.
The forward /sdlc pipeline propagates intent downstream: issue, requirements, specification, plan, tasks, tests, code.
This skill is its complement.
It propagates reality upstream: starting from the code and tests as ground truth, it walks back through tasks, plan, specification, requirements, and the issue, checking each adjacent pair for bidirectional consistency.
The core problem this skill solves: artifacts go stale.
Code evolves past the spec without updating it.
A requirement is dropped during implementation but never removed from requirements.md.
A test case (TC-7) survives after the behavior it covered was deleted.
A plan task references FR-4, which no longer exists.
Each review-* phase checks one artifact in isolation against its immediate input.
None of them re-walks the whole chain end to end after the fact.
This skill does exactly that, and it is the only skill that builds a full traceability matrix from code back to the original issue.
Prerequisites
- Working directory is the root of the repository
- A populated
.sdlc/directory (run/sync-sdlcfirst if absent) - At least one feature under
.sdlc/features/N-<slug>/with artifacts present - Read access to the codebase (the code is the ground truth)
- Read any files under
.sdlc/context/for project-level conventions and apply their style rules to the produced report
What This Skill Catches
| Drift | Example | Reverse Pass That Detects It |
|---|---|---|
| Orphan downstream (scope creep) | Code implements a behavior that no requirement or spec describes | Code ↔ Spec |
| Orphan upstream (unrealized intent) | An FR-2 in requirements.md has no implementation, task, or test |
Every pass, upstream direction |
| Stale spec | specification.md describes an API endpoint that was renamed or removed | Spec ↔ Code |
| Dangling test | TC-5 covers a behavior that no longer exists in code |
Tests ↔ Code |
| Missing coverage | A task or spec section has no corresponding test case | Tasks ↔ Tests, Spec ↔ Tests |
| Broken task link | A task references FR-4 which is not in requirements.md |
Tasks ↔ Requirements |
| Plan divergence | plan.md lists phases that do not map to any spec section | Plan ↔ Spec |
| Requirements drift | requirements.md lists an acceptance criterion with no matching AC in tests | Requirements ↔ Tests |
| Telemetry gap | telemetry.md defines an event never emitted by the code | Telemetry ↔ Code |
| Observability gap | observability.md defines a metric or alert the code never produces | Observability ↔ Code |
| Lifecycle drift | lifecycle.md documents a state or transition the code no longer implements, or the code has states not documented | Lifecycle ↔ Code |
| Doc drift | documentation describes a parameter the code no longer accepts | Docs ↔ Code |
| ID corruption | A cross-reference like FEAT-1-FR-7 points to nothing |
ID Integrity |
| Review gap | specification.md has no approved review while tasks are done |
Review-approval monotonicity |
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.
- 2mo ago First seen · 381 lines · 70 tokens per session scan A 65abc5e83c6f
backpropagate-sdlc is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 4,723 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…