Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/meltforce/FreeRepsnpx agentmods add skills/meltforce/freereps/verifyWrote 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/meltforce/freereps/verify)<a href="https://agentmods.dev/skills/meltforce/freereps/verify"><img src="https://agentmods.dev/badge/skills/meltforce/freereps/verify/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/meltforce/freereps/verify"><img src="https://agentmods.dev/badge/skills/meltforce/freereps/verify.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 | $0.00097 | $0.01347 |
| Opus 5.5 | $0.00039 | $0.00539 |
| Sonnet 5.5 | $0.00019 | $0.00269 |
| Haiku 4.5 | $0.00010 | $0.00135 |
Grade A, and why
verify scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS "$F/actions/runs?limit=5" # -> run id, newest first How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify
Run from the repo root. The order below is cheapest-first: a failure in step 1 makes the rest irrelevant.
1. Go
mkdir -p server/web/dist && touch server/web/dist/.gitkeep # only if dist is absent
cd server && go build ./... && go vet ./... && go test ./...
The stub matters: server/web.go embeds web/dist via go:embed, and without
the directory the build fails with an embed error that names the directive
rather than the missing directory.
go test ./... skips the integration tests. Those need a running TimescaleDB and
run with go test -tags integration ./... — run them when the change touches
server/internal/storage/ or a migration, because the unit tests do not execute
a single SQL statement against a real server. The aggregation tests in
server/internal/storage/aggregation_integration_test.go are the reason that
matters: they check figures, and a unit test that inspects the generated SQL
string proves the shape and nothing about the numbers.
A scratch database for them, in the version the deployment runs:
export PATH="/Applications/Docker.app/Contents/Resources/bin:$PATH" # CLI is not on the tool-call PATH
docker run -d --name freereps-scratch \
-e POSTGRES_DB=freereps_scratch -e POSTGRES_USER=freereps \
-e POSTGRES_PASSWORD=scratch -p 55432:5432 \
timescale/timescaledb:latest-pg16
FREEREPS_TEST_DSN="postgres://freereps:scratch@localhost:55432/freereps_scratch?sslmode=disable" \
go test -tags integration ./internal/storage/
The harness refuses to run against a database named freereps and removes only
its own user's rows, so a scratch database shared with other tests keeps its
contents.
2. golangci-lint
tools/lint.sh
Run it from the repo root; make lint calls the same script. It reads the
pinned version from .forgejo/workflows/ci.yml, installs that version when the
binary at $(go env GOPATH)/bin/golangci-lint is absent or older, and runs it
over server/.
Do not reach for the bare golangci-lint instead. ~/go/bin is not on the
PATH a tool call inherits on the development Macs, so command -v reports the
linter as missing; and a binary built with an older Go toolchain than
server/go.mod targets refuses to load the configuration. Both read like an
absent installation. Skipping the step lets findings that only the linter
reports, such as errcheck on a discarded fmt.Fprint result, through to CI.
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 Changed · -4 lines 7ec76750a3fd
- 23d ago Changed 0b2fe186c423
- 25d ago Changed · +10 lines b847d5eefdbc
- 26d ago Changed · +19 lines 9bfe7f65c22b
- 1mo ago First seen · 96 lines · 97 tokens per session scan A c9f0dc5999c4
verify is a skill published in the GitHub repository meltforce/FreeReps (17 stars, last pushed 3d ago), licensed MIT. It adds 97 tokens to every session and 1,347 once invoked, about $0.0004 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 skills, from other repositories
hevy-workouts
Use when the user asks to inspect, summarize, plan, log, or update Hevy workouts, routines, exercises, or body measurements.
flutter-mcp-toolkit-control
Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.
coding-agents-hooks-authoring
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
flutter-mcp-e2e-harness
Use this skill when writing or running repeatable E2E scenarios for Flutter apps as checked-in Dart with the fluttermcpharness package (packages/harness) — build/launch the app, attach to its VM service, drive widgets (snapshot/tap/enter text) and assert without MCP; also covers the repo showcase launcher (make…
harness-engineering-lifecycle
Design, implement, and integrate generalized validation harnesses across a producer-consumer boundary after a local harness contract exists. Use when refactoring custom validation CLIs/MCPs for large polyrepos, extending Steward across sibling repos, or deploying a local tool to a consumer project for dogfooding and…
flutter-mcp-toolkit-dogfood-iterations
Runs and records showcase/fluttertestapp dogfood iterations (toolqualityrubric, rundogfoodeval.sh, dogfoodwebeval.yaml). Use when scoring MCP/intentcall quality, appending iteration N, comparing regressions, or CI static/weekly eval gates.