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.
git clone --depth 1 https://github.com/fockus/skill-memory-bankWrote 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/commands/fockus/skill-memory-bank/api-contract)<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/api-contract"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/api-contract/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/commands/fockus/skill-memory-bank/api-contract"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/api-contract.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 | $0.00039 | $0.01295 |
| Opus 5.5 | $0.00016 | $0.00518 |
| Sonnet 5.5 | $0.00008 | $0.00259 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
api-contract scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **gRPC**: `buf curl` + generated client stubs How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Contract: $ARGUMENTS
Skill bundle root
Every bundled helper below runs through the skill bundle root, never a bare scripts/… path (the
working directory is the user's project, where scripts/ is absent or belongs to someone else):
SKILL_DIR="${MB_SKILLS_ROOT:-${SKILL_DIR:-$HOME/.claude/skills/memory-bank}}"
[ -f "$SKILL_DIR/scripts/_lib.sh" ] || { echo "mb: skill bundle not found at $SKILL_DIR — set MB_SKILLS_ROOT" >&2; exit 2; }
0. Validate arguments
If $ARGUMENTS is empty, stop and ask the user which action to perform (generate, check, test).
1. Stack detection
eval "$(bash "$SKILL_DIR"/scripts/mb-metrics.sh)"
If stack=unknown, ask the user for the framework / language in use.
2. Detect the API type
# OpenAPI / Swagger
find . -name "*.yaml" -o -name "*.yml" 2>/dev/null | xargs grep -l "openapi\|swagger" 2>/dev/null
find . -name "openapi*" -o -name "swagger*" 2>/dev/null
# gRPC / Protobuf
find . -name "*.proto" 2>/dev/null
# GraphQL
find . -name "*.graphql" -o -name "*.gql" 2>/dev/null
# Handler detection across frameworks:
# Go (gin / echo / chi / net/http)
grep -rn "func.*Handler\|func.*http\.\|r\.GET\|r\.POST\|e\.GET\|e\.POST\|http\.HandleFunc" --include="*.go" . | head -30
# Node.js — Express / Fastify / Nest
grep -rn "app\.\(get\|post\|put\|delete\|patch\)\|router\.\(get\|post\)\|@Get\|@Post" --include="*.ts" --include="*.js" . | head -30
# Python — FastAPI / Flask / Django
grep -rn "@app\.\(get\|post\|put\|delete\)\|@router\.\(get\|post\)\|@app\.route\|path(" --include="*.py" . | head -30
# Java / Kotlin — Spring
grep -rn "@GetMapping\|@PostMapping\|@PutMapping\|@DeleteMapping\|@RequestMapping" --include="*.java" --include="*.kt" . | head -30
# .NET
grep -rn "\[HttpGet\]\|\[HttpPost\]\|\[HttpPut\]\|\[HttpDelete\]\|MapGet\|MapPost" --include="*.cs" . | head -30
# Rust — Axum / Actix / Rocket
grep -rn "\.route(\|#\[get\|#\[post\|#\[put\|#\[delete" --include="*.rs" . | head -30
# Ruby — Rails
grep -rn "resources \|get \|post \|put \|delete " --include="routes.rb" . | head -30
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.
- 12d ago Changed · +23 tokens per session 51e8eab97774
- 21d ago Changed · +10 lines 26e913abf077
- 1mo ago First seen · 116 lines · 16 tokens per session scan A 0f7a0618a809
api-contract is a command published in the GitHub repository fockus/skill-memory-bank (26 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,295 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
dare-laravel-api
Padrões DARE para APIs REST em Laravel 11 + PHP 8.3. Strict Types, FormRequests, Services, Resources, Repositories, Eloquent + casts, tratamento global de exceções, testes Pest, PHPStan/Larastan nível 8.
unity-ralph
Relentless verify-fix loop — refuses to stop until the project is clean. Runs unity-verifier repeatedly with configurable max iterations and stall detection.
unity-test
Writes missing tests and runs them via MCP. Identifies untested code, creates EditMode/PlayMode tests, executes via runtests, reports results.
api-mock
Build realistic mock APIs for development, testing, or demos.
tdd
Start test-driven development workflow for a feature or fix.
test-coverage
Analyze test coverage and add missing tests to reach 80%.