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 LerianStudio/ring --skill reconciling-predev-docsgit clone --depth 1 https://github.com/LerianStudio/ringWrote 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/lerianstudio/ring/reconciling-predev-docs)<a href="https://agentmods.dev/skills/lerianstudio/ring/reconciling-predev-docs"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/reconciling-predev-docs/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/lerianstudio/ring/reconciling-predev-docs"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/reconciling-predev-docs.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 | $0.00115 | $0.01387 |
| Opus 5 | $0.00057 | $0.00694 |
| Sonnet 5 | $0.00023 | $0.00277 |
| Haiku 4.5 | $0.00012 | $0.00139 |
Grade A, and why
ring:reconciling-predev-docs 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 5d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Doc Review
When to use
- Before starting dev-cycle (validate doc quality as a pre-gate)
- After completing pre-dev workflow (ring:planning-small-features or ring:planning-large-features)
- When user requests project documentation review
- After significant changes to reference docs (PRD, TRD, OpenAPI spec, schema, plan)
Skip when
- Code review needed (use ring:reviewing-code instead)
- Docs do not exist yet (run pre-dev workflow first)
- Reviewing a single simple file (do it directly without the skill)
Sequence
Runs before: ring:running-dev-cycle, ring:writing-plans Runs after: ring:planning-small-features, ring:planning-large-features
Related
Complementary: ring:writing-prds, ring:writing-trds, ring:designing-api-contracts, ring:designing-data-model, ring:writing-plans Differentiation: ring:reviewing-code reviews code. ring:reconciling-predev-docs reviews documentation artifacts against each other.
Adapted from alexgarzao/optimus (optimus-deep-doc-review)
Deep cross-reference review of project documentation to catch contradictions before they become implementation bugs. Emphasis is on inconsistencies between docs, not just intra-doc quality.
Phase 0: Discover and Load Docs
Step 0.1: Identify Docs to Review
If user specified files, use those. Otherwise, auto-discover:
Search locations:
docs/pre-dev/<feature>/(Ring pre-dev artifacts)docs/(general project docs)- Root directory (README, CHANGELOG, ARCHITECTURE)
Include: research.md, prd.md, feature-map.md, trd.md, openapi.yaml, schema file (schema.sql / schema.prisma), dependencies.md, plan.md, design-validation.md (if present), coding standards, README, CHANGELOG
Exclude: generated files, node_modules, build artifacts, binary files, test fixtures
Present discovered docs list to user before proceeding.
Step 0.2: User Confirms Scope
Show doc list and ask: "Are there additional documents to include or any to exclude?"
Step 0.3: Load All Docs
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.
- 5d ago First seen · 137 lines · 115 tokens per session scan A 6448f88b2cd5
ring:reconciling-predev-docs is a skill published in the GitHub repository LerianStudio/ring (211 stars, last pushed 20d ago), licensed Apache-2.0. It adds 115 tokens to every session and 1,387 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
calibration
Internal dynos-work skill. Agent calibration — generates project-specific agents, benchmarks them, promotes/demotes based on performance, and manages auditor mode transitions. Runs only when the user explicitly types /dynos-work:calibration; never auto-triggered from conversation.
maintain
Internal dynos-work skill. Autonomous maintenance worker. Scans the repo for technical debt, security anti-patterns, and architectural drift; on a finding it creates a repair branch, implements the fix, verifies with audits/tests, and opens a Pull Request. Runs only when the user explicitly types /dynos-work:maintain…
ds-brief
Data-backed brief — research, source, double-verify, and render a visually rich single-file HTML report. Use when the user wants a sourced, fact-checked brief or report on a topic.
ds-ship
Ship orchestrator — classify the project, pick a mode (improve/release/launch/maintain), delegate only the skills the project's signals justify, consolidate findings, produce an audit report. Use for an end-to-end audit or ship pipeline across multiple skills.
trajectory
Internal dynos-work skill. Sequence memory manager. Stores compact task traces and retrieves similar prior tasks to inform discovery and design review. Runs only when the user explicitly types /dynos-work:trajectory; never auto-triggered from conversation.
ds-deploy
Deployment and infrastructure — containerization, deployment, monitoring, incident response. Use when deploying an app, setting up containers/monitoring, or planning incident response.