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 HigorAlves/orc --skill adr-writinggit clone --depth 1 https://github.com/HigorAlves/orcWrote 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/higoralves/orc/adr-writing)<a href="https://agentmods.dev/skills/higoralves/orc/adr-writing"><img src="https://agentmods.dev/badge/skills/higoralves/orc/adr-writing/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/higoralves/orc/adr-writing"><img src="https://agentmods.dev/badge/skills/higoralves/orc/adr-writing.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 | $0.00050 | $0.01115 |
| Opus 5 | $0.00025 | $0.00558 |
| Sonnet 5 | $0.00010 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
adr-writing 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Writing
Defer to
orc:doc-writingfor the shared scaffolding: the doc-type map (ADR vs PRD vs TRD vs RFC vs postmortem, and how ADRs differ from RFCs and plans), the shared section outline, thedocs/<type>s/NNNN-*.mdnumbering & publication convention, and the review gates. This skill carries only the ADR-specific template, status transitions, and tone.
ADRs are the contract between past-you and future-you. They capture why a decision was made, not just what was chosen, so a year later nobody has to reverse-engineer the trade-offs from code.
When to write one
Write an ADR when all of these are true:
- The decision is architectural — affects multiple modules, defines a boundary, picks a technology, or sets a convention everyone follows.
- The decision is non-obvious — there were real alternatives, and another smart engineer might pick differently.
- The decision is durable — you expect it to live ≥ 3 months. Tactical tweaks don't deserve ADRs.
Don't write ADRs for:
- Library version bumps with no API impact
- Bug fixes
- Naming choices inside a single file
- Decisions you'll revisit next sprint
Note: ADRs live at docs/adr/NNNN-<kebab-decision-name>.md (singular adr dir name by convention). All other numbering mechanics are the shared convention in orc:doc-writing.
Template
Every ADR uses this shape:
# NNNN — <Decision title in noun phrase>
- **Status:** Proposed | Accepted | Superseded by NNNN | Deprecated
- **Date:** YYYY-MM-DD (when status was last updated)
- **Deciders:** <names or roles>
## Context
What is the situation that demanded a decision? What forces are at play (technical, organizational, regulatory)? Quote real numbers, real constraints, real deadlines. 1–3 paragraphs.
## Decision
The chosen approach, stated as a single declarative sentence. Then 1–3 paragraphs explaining how it works in this codebase.
## Alternatives considered
Each alternative gets a short subsection:
### Option A — <name>
- What it would look like
- Why it was rejected (one or two specific reasons)
### Option B — <name>
…
Include "do nothing" as an alternative if it was real.
## Consequences
What changes because of this decision?
- **Positive:** <what gets easier, safer, faster>
- **Negative:** <what gets harder, more brittle, more locked in>
- **Neutral:** <visible side-effects without strong polarity>
Be honest about negatives. An ADR with no negatives is a sales pitch, not a record.
## Follow-ups
- [ ] Concrete tasks unlocked by accepting this decision (link to issues/PRs).
- [ ] Open questions to revisit later, with a date.
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 · 103 lines · 50 tokens per session scan A 186a6b817e18
adr-writing is a skill published in the GitHub repository HigorAlves/orc (6 stars, last pushed 13d ago), licensed MIT. It adds 50 tokens to every session and 1,115 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.