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/managedcode/geminisharpsdk/mcaf-adr-writingnpx skills add managedcode/GeminiSharpSDK --skill mcaf-adr-writinggit clone --depth 1 https://github.com/managedcode/GeminiSharpSDKWrote 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/managedcode/geminisharpsdk/mcaf-adr-writing)<a href="https://agentmods.dev/skills/managedcode/geminisharpsdk/mcaf-adr-writing"><img src="https://agentmods.dev/badge/skills/managedcode/geminisharpsdk/mcaf-adr-writing.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 | $0.00082 | $0.00726 |
| Opus 5 | $0.00041 | $0.00363 |
| Sonnet 5 | $0.00016 | $0.00145 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
mcaf-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 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCAF: ADR Writing
Outputs
docs/ADR/ADR-XXXX-<short-title>.md(create or update)- Update
docs/Architecture/Overview.mdwhen boundaries/interactions change
Decision Quality (anti-guesswork checklist)
Before writing, make the ADR executable (no placeholders, no hand-waving):
- Decision: one sentence. If you can’t write it, you don’t have a decision yet.
- Scope: what changes / what does not + which module(s) are affected (match
docs/Architecture/Overview.mdnames). - No invented reality: every component you mention exists in the repo today, or is explicitly part of this change (named + where it will live).
- Invariants: write as MUST / MUST NOT statements and say how we prove each (test or static analysis).
- Verification: use exact commands from
AGENTS.mdand link scenarios → test IDs. - Stakeholders: Product / Dev / DevOps / QA — what each role must know to execute safely.
Workflow
- Confirm the decision scope:
- what changes (and what does not)
- what module(s) are affected
- follow
AGENTS.mdscoping rules: Architecture map → linked ADR/Feature → entry points (do not scan everything)
- Start from
docs/templates/ADR-Template.md.- keep the ADR’s
## Implementation plan (step-by-step)updated while executing
- keep the ADR’s
- Write the ADR as a decision record:
- Context: constraints + why this is needed now
- Decision: a short, direct statement
- Diagram (mandatory): include at least one Mermaid diagram for the decision (boundaries/modules/interactions)
- Alternatives: 1–3 realistic options with pros/cons
- Consequences: trade-offs, risks, mitigations
- Make it executable for the team:
- follow
AGENTS.mdTask Delivery rules (analysis → plan → execute → verify) - include the invariants that must be proven by tests
- include verification commands copied from
AGENTS.md - include rollout/rollback and “how we know it’s safe”
- follow
- Make impacts explicit:
- code/modules affected
- data/config changes (including migration/rollback)
- backwards compatibility strategy
- Add verification that proves the decision:
- which tests must exist/change
- which suites must stay green
- If the decision changes boundaries, update
docs/Architecture/Overview.md(diagram, modules table, dependency rules).
What ships with it
1 file 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 · 58 lines · 82 tokens per session scan A 72e8e44a72a4
mcaf-adr-writing is a skill published in the GitHub repository managedcode/GeminiSharpSDK (2 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 726 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
security-patcher
Invoke this as your absolute first action before using any other tools whenever a user requests to fix, patch, or remediate a vulnerability. Do not perform manual research first.
dependency-manager
Safely resolve and install isolated dependencies for isolated sandboxes (PoC execution).
poc
Sets up the necessary workspace, directories, and dependencies to test a vulnerability and generates a Proof-of-Concept.
architecture
Project architecture and file structure conventions for all process types. Use when: (1) Creating new files or modules, (2) Deciding where code should go, (3) Converting single-file components to directories, (4) Reviewing code for structure compliance, (5) Adding new bridges, services, agents, or workers.
testing
Testing workflow and quality standards for writing and running tests. Use when: (1) Writing new tests, (2) Adding a new feature that needs tests, (3) Modifying logic that has existing tests, (4) Before claiming a task is complete.
conductor-new-track
Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.