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 yuri-semenenko/ai-engineering-workspace --skill adrgit clone --depth 1 https://github.com/yuri-semenenko/ai-engineering-workspaceWrote 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/yuri-semenenko/ai-engineering-workspace/adr)<a href="https://agentmods.dev/skills/yuri-semenenko/ai-engineering-workspace/adr"><img src="https://agentmods.dev/badge/skills/yuri-semenenko/ai-engineering-workspace/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 5.1 | $0.00073 | $0.00795 |
| Opus 5 | $0.00036 | $0.00398 |
| Sonnet 5 | $0.00015 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
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 7d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR
Record a concrete architectural decision in a format optimized for future readers — typically the team member six months from now wondering "why did we do it this way?"
ADRs are not exploratory. If the user is still weighing options, redirect to /rfc. ADRs assume the decision is made (or being made in this moment) and the job is to capture context + reasoning before they decay.
Steps
- Confirm the decision is actually settled. If the user describes multiple options without picking one, say so and suggest
/rfcinstead. - Find the repo's ADR location. Check
docs/adr/,docs/decisions/,adr/,.adr/. Mirror existing numbering and naming (0042-use-postgres-jsonb-for-events.mdstyle). If none exists, proposedocs/adr/0001-<slug>.mdand let the user confirm. - Look for an ADR template in the repo (
docs/adr/template.md,adr-template.md). If present, follow it exactly. Otherwise use the structure below. - Date the ADR. Use today's date in
YYYY-MM-DD. - Status starts as "Accepted" unless the user is recording a historical decision now superseded (then
Superseded by ADR-NNNN) or one still in review (Proposed).
Default structure (when no repo template exists)
# ADR-NNNN: <Short decision title>
- **Status:** Accepted
- **Date:** YYYY-MM-DD
- **Deciders:** <names or roles>
## Context
What forces are at play? What's the problem and constraints? Keep it to what's
needed to understand the decision — not the full history of the project.
## Decision
We will <action verb> <thing>. State the choice plainly. One paragraph max.
## Consequences
### Positive
- ...
### Negative
- ...
### Neutral
- What changes operationally / for new contributors / for adjacent systems.
## Alternatives Considered
Brief — one or two sentences each. Why each was rejected. This is not an RFC;
do not re-litigate the full trade-off table.
## References
- Linked RFC, PR, ticket, prior ADR, external doc.
Rules
- One decision per ADR. If the user is describing two decisions, write two ADRs.
- Don't invent Deciders. Infer from git config, PR author, or commit author. If you can't determine them, write
<TBD>and ask the user — never fabricate names or roles. - No marketing prose. "We have decided to leverage the strategic synergies of..." — no. "We will use Postgres jsonb instead of a separate events table because..." — yes.
- Past-tense context, present-tense decision, future-tense consequences. ("X was painful because... → We will use Y → New contributors will need to...")
- Immutable after acceptance. If the decision changes, write a new ADR that supersedes this one. Do not silently edit history. Mention this rule to the user when they ask to "update" an accepted ADR.
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.
- 7d ago First seen · 71 lines · 73 tokens per session scan A c0e13134461e
adr is a skill published in the GitHub repository yuri-semenenko/ai-engineering-workspace (1 stars, last pushed 7d ago), licensed MIT. It adds 73 tokens to every session and 795 once invoked, about $0.0004 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
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
My Skill
Content here.
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
spec-authoring
Reference material for writing product, technical, and operational specifications (work-item priorities, requirement families, success criteria). Loaded on demand by specify-feature; not directly invokable.
audit
Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…