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-feature-specnpx skills add managedcode/GeminiSharpSDK --skill mcaf-feature-specgit clone --depth 1 https://github.com/managedcode/GeminiSharpSDKWhat 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 | $0.00075 | $0.00612 |
| Opus 5 | $0.00037 | $0.00306 |
| Sonnet 5 | $0.00015 | $0.00122 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
mcaf-feature-spec 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 yesterday.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCAF: Feature Spec
Outputs
docs/Features/<feature>.md(create or update)- Update links from/to ADRs and architecture map when needed
Spec Quality (anti-guesswork checklist)
Write a spec that can be implemented and verified without guessing:
- No placeholders: avoid “TBD”, “later”, “etc.”; if something is unknown, list it as an explicit question.
- Concrete modules: use real module/boundary names from
docs/Architecture/Overview.md. - Rules are testable: numbered business rules with clear inputs → outputs (no vague adjectives).
- Flows are executable: scenarios include preconditions, steps, expected results (happy + negative + edge).
- Verification is real: commands copied from
AGENTS.md, and scenarios mapped to test IDs. - Stakeholders covered: Product / Dev / DevOps / QA each get the information they need to ship safely.
Workflow
- Start from
docs/Architecture/Overview.mdto pick the affected module(s). - Create/update the feature doc using
docs/templates/Feature-Template.md.- follow
AGENTS.mdscoping rules (do not scan the whole repo; use the architecture map to stay focused) - keep the feature’s
## Implementation plan (step-by-step)updated while executing
- follow
- Define behaviour precisely:
- purpose and scope (in/out)
- business rules (numbered, testable)
- primary flow + edge cases
- Describe system behaviour in terms of entry points, reads/writes, side effects, idempotency, and errors.
- Add a Mermaid diagram for the main flow (modules + interactions; keep it readable).
- Write verification that can be executed:
- test environment assumptions
- concrete test flows (positive/negative/edge)
- mapping to where tests live (or will live)
- traceability: rules/flows → test IDs (so tests reflect the spec)
- Keep Definition of Done strict:
- behaviour covered by automated tests
- static analysis clean
- docs updated (feature + ADR + architecture overview if boundaries changed)
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.
- yesterday First seen · 51 lines · 75 tokens per session scan A 7aeb0a2d0713
mcaf-feature-spec is a skill published in the GitHub repository managedcode/GeminiSharpSDK (2 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 612 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-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.