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 me-cedric/agent-compass --skill adrgit clone --depth 1 https://github.com/me-cedric/agent-compassWrote 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/me-cedric/agent-compass/adr)<a href="https://agentmods.dev/skills/me-cedric/agent-compass/adr"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/adr/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/me-cedric/agent-compass/adr"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/adr.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 | $0.00044 | $0.00523 |
| Opus 5.5 | $0.00018 | $0.00209 |
| Sonnet 5.5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
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 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.
What it actually says
adr
Record a decision that is structural and costly to undo: architecture, a shared contract, data ownership, build or buy, a cross-cutting convention.
Skip a local choice that the code already shows.
For the architecture of a new project, use architecture-advisor.
Steps
- Find
{{ADR_DIR}}. Create it if it does not exist. - Use the template in that directory when one exists. Its name starts with
templateoradr-template. Else use the shape below. - Take the next number: the highest
NNNNplus one, in four digits. Name the fileNNNN-kebab-title.md. - Extract from the source. Do not invent. Take the problem, the forces, each option, its pros and cons, the choice, the reasons and the follow-ups.
- Attribute nothing that the source does not support.
- Keep every rejected option with the reason that it lost.
- Set
status: proposed. Setacceptedonly when the meeting ratified the decision. - Set
dateto the meeting date. Filldecision-makers,consultedandinformedonly from the source. - Write each gap as an open question or a follow-up under Consequences.
- Link both ways. Link the module README or design note to the ADR. Link the ADR to the spec, the issue and the PR.
- Report the path and a one-line summary.
Shape (MADR 4)
---
status: proposed
date: <YYYY-MM-DD>
decision-makers: []
---
# <short title>
## Context and problem statement
## Decision drivers
## Considered options
## Decision outcome
Chosen option: "<option>", because <reason>.
### Consequences
## Pros and cons of the options
## More information
Rules
- Fill every section, or write
N/A. - Supersede, never rewrite. A reversed decision gets a new ADR. Change the status of the old ADR to
superseded by NNNN. - Change an
acceptedADR only in its status. - Do not commit.
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 · 55 lines · 44 tokens per session scan A 86b8a51f27cb
adr is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 523 once invoked, about $0.0002 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 2026-10-18.
Other skills, from other repositories
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.