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 assisjp/specflow --skill repo-hardeninggit clone --depth 1 https://github.com/assisjp/specflowWrote 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/assisjp/specflow/repo-hardening)<a href="https://agentmods.dev/skills/assisjp/specflow/repo-hardening"><img src="https://agentmods.dev/badge/skills/assisjp/specflow/repo-hardening/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/assisjp/specflow/repo-hardening"><img src="https://agentmods.dev/badge/skills/assisjp/specflow/repo-hardening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 100 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 20 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00144 | $0.02371 |
| Opus 5 | $0.00072 | $0.01185 |
| Sonnet 5 | $0.00029 | $0.00474 |
| Haiku 4.5 | $0.00014 | $0.00237 |
Grade A, and why
repo-hardening 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 9d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Hardening
Ensure a deterministic verification layer exists in the repository, and that it is recorded where agents read.
Principle: an error a machine can catch, a model should never have to. Every check here is an agent cycle and a human review saved.
Idempotent. Re-running re-verifies and corrects drift — it never duplicates.
Inviolable rules
- Never overwrite existing config. If it exists, adopt it and record it.
- Never install a second hook manager. A repo has at most one.
- Never change an existing CI rule. Only add, and only with authorisation.
- Never make a bulk change without confirmation.
- Never write outside your own markers in the agent-context file (
AGENTS.md/CLAUDE.md). - Never create or edit
CONTEXT.md, ADRs, or domain docs. Those have another owner (domain-modeling). - Stop and ask whenever a choice is irreversible or opinionated.
Phase 1 — Inventory
Write nothing in this phase.
Ecosystem — detect from the manifest:
| File | Ecosystem |
|---|---|
package.json |
Node/TS |
pyproject.toml, requirements.txt, setup.py |
Python |
go.mod |
Go |
Cargo.toml |
Rust |
mix.exs |
Elixir |
Gemfile |
Ruby |
composer.json |
PHP |
pom.xml, build.gradle |
JVM |
Multiple manifests or a monorepo: list them all and ask which is in scope.
What already exists:
- hook manager:
.husky/,lefthook.yml,.pre-commit-config.yaml,.githooks/,core.hooksPath, a.git/hooks/with real content - formatter, linter, type-checker config
- test runner and where tests live
- CI:
.github/workflows/,.gitlab-ci.yml - scripts in the manifest, Makefile, justfile
- run/dev command for the evidence gate — a
dev/start/servescript, a documented run command, or none (a library with no runnable surface) AGENTS.md,CLAUDE.md,CONTRIBUTING.md— which one the harness auto-loads, and whether arepo-hardeningblock is already inside
Health of what exists — run the checks you found and count the failures. A linter configured but unrun for two years is not a verification layer, it is a liability.
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.
- 9d ago First seen · 141 lines · 144 tokens per session scan A 164e2de77594
repo-hardening is a skill published in the GitHub repository assisjp/specflow (17 stars, last pushed 1mo ago), licensed MIT. It adds 144 tokens to every session and 2,371 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
migrate-vstest-to-mtp
Use this skill before answering, planning, or editing whenever .NET tests or CI are switching from VSTest to Microsoft.Testing.Platform (MTP), or an MTP migration behaves differently. Triggers include "switch from VSTest"; MSTest/NUnit/xUnit MTP enablement; OutputType=Exe only for test projects in…
ci
Configure Ginkgo for continuous integration — the recommended CLI flag set and the rationale for each flag (-r -p --randomize-all --randomize-suites --fail-on-pending --fail-on-empty --keep-going --cover --race --trace --json-report --timeout --poll-progress-after/-interval), invoking via go run to pin the CLI to…
playwright-ci
Production-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.
playwright-testing
E2E testing with Playwright - Page Objects, cross-browser, CI/CD.
ci-maintenance-workflow
CI and GitHub Actions maintenance workflows — fix a failing test from a CI URL, fix a failing smoke test, add @pytest.mark.slow markers to slow tests, or review a PR against agent-checkable standards. Use when user asks to fix a failing test, fix a smoke test, mark slow tests, or review a PR. Trigger when the user…
test-setup
Scaffold the test framework and CI/CD pipeline for the project's engine. Creates the tests/ directory structure, engine-specific test runner configuration, and GitHub Actions workflow. Run once during Technical Setup phase before the first sprint begins.