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 agentmods add skills/luanmorenommaciel/agentspec/github-cr-adrnpx skills add luanmorenommaciel/agentspec --skill github-cr-adrgit clone --depth 1 https://github.com/luanmorenommaciel/agentspecWrote 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/luanmorenommaciel/agentspec/github-cr-adr)<a href="https://agentmods.dev/skills/luanmorenommaciel/agentspec/github-cr-adr"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/github-cr-adr.svg" alt="Measured on agentmods" 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 | $0.00137 | $0.02424 |
| Opus 5 | $0.00068 | $0.01212 |
| Sonnet 5 | $0.00027 | $0.00485 |
| Haiku 4.5 | $0.00014 | $0.00242 |
Grade A, and why
github-cr-adr 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 3d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create ADR (GitHub)
Draft one Architecture Decision Record as an ephemeral local file, ready to be reviewed and then published as a GitHub issue by github-post-issue.
An ADR records one durable architecture decision so it is never re-litigated from scratch. Its value is the why and the trade-offs, not just the final choice. The published ADR must stand alone: GitHub is the project's state store, agent sessions are stateless workers, and the issue is the complete record — any future contributor or agent session must be able to read it with zero private context.
This skill always operates on the repository it is invoked in — the repo is detected dynamically in step 1 and never assumed.
When to use
- The decision is architecturally significant: it shapes structure, dependencies, interfaces, non-functional characteristics, or construction techniques.
- The decision is expensive to reverse, and a future contributor will need to understand why it was made.
- The user wants to formalize a decision already reached in discussion, so the reasoning survives the session.
Skip if
| Situation | Do instead | Why |
|---|---|---|
| Feature, task, bug, spike, or epic | github-cr-issue |
Routine work items are not architecture decisions. |
| Small, low-risk, easily reversible choice | Decide in the PR or issue thread | Log bloat drowns out the decisions that matter. |
| Temporary measure (POC, workaround, experiment) | Note it in the related issue | ADRs record durable decisions, not scaffolding. |
| Topic already covered by an existing ADR or standard | Comment on or amend the existing record | One decision, one record — duplicates fork the history. |
Workflow
1. Search for existing coverage — before writing anything
Catching a duplicate before drafting costs one search; catching it at publish time costs a fully written body. Detect the consumer's repository dynamically:
REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner)
# Fallback when gh cannot resolve the repo:
[ -z "$REPO" ] && REPO=$(git remote get-url origin | sed -E 's#(git@|https://)github.com[:/]##; s#\.git$##')
gh issue list --repo "$REPO" --search "<decision keywords>" --state all --limit 20
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 165 lines · 137 tokens per session scan A dd6023506d6d
github-cr-adr is a skill published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed yesterday), licensed MIT. It adds 137 tokens to every session and 2,424 once invoked, about $0.0007 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 2026-09-01.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.
finn-spec
Interview the user about a raw idea until confident, then file a build-ready issue in Linear. Use when asked to run Finn-loop's spec interview, draft a queue-ready issue, or plan a feature. Interactive — requires the user present; never run unattended.
create-milestone
Creates a GitHub milestone on the current repository and returns its number for downstream use. Use when starting a new sprint, release, or theme grouping of backlog items. No args triggers guided intake (title, due date, description); 'quick {title}' skips to description only. Checks for duplicates before creating.…