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 hecatehq/hecate --skill testergit clone --depth 1 https://github.com/hecatehq/hecateWrote 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/hecatehq/hecate/tester)<a href="https://agentmods.dev/skills/hecatehq/hecate/tester"><img src="https://agentmods.dev/badge/skills/hecatehq/hecate/tester.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
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 →
- medium Memory Poisoning · line 26 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 29 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 26 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 27 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 28 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 29 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00032 | $0.00962 |
| Opus 5 | $0.00016 | $0.00481 |
| Sonnet 5 | $0.00006 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
hecate-tester 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 8d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hecate tester skill
Test-strategy responses. Push for evidence, not assumptions.
When to use
Every change that adds or modifies behavior. Also:
- Before creating a PR, pushing new commits to a PR, marking it ready, or asking for merge — identify and run the related tests first.
- Bug fix — a regression test pinning the fix is required.
- Production-code change — automated coverage in the same change is required unless the PR/update summary explains why automation cannot reach the risk.
- Coverage audit — what's tested, what isn't, what's risky.
- Refactor with risky surface — pin behavior before reshaping.
- SSE / streaming behavior — partial output, mid-stream cancel, reconnect.
- Sandbox-boundary changes — subprocess lifecycle, network egress.
Test layer choice matrix
| Layer | Use for |
|---|---|
| Unit | Pure data transformation. Wire-shape passthrough. Error classification. Retry/failover decisions. Streaming wire shape (per-event SSE translation, usage accumulation). agent_loop tool dispatch. MCP tool registration. UI data-to-prop transformation. Conditional rendering of critical states. Form-input parsing and submit-payload shaping. |
| Integration | Multi-package wiring within the gateway. Examples: governor + usage store; router + retention worker; orchestrator + taskstate. |
| E2E | e2e/ directory, build tag e2e. Required when behavior depends on the real binary running: api → orchestrator → providers chain end-to-end; subprocess lifecycle (sandbox, mcp stdio host); startup or config-loading semantics; durable SQLite behavior across restart; Postgres smoke when behavior depends on the real pgx/Postgres dialect; new SSE event sequences operators rely on; public HTTP contract changes that downstream SDKs see. UI e2e via Playwright when a journey spans multiple operator screens or depends on the real gateway responding. |
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.
- 8d ago First seen · 72 lines · 32 tokens per session scan A e64d89259403
hecate-tester is a skill published in the GitHub repository hecatehq/hecate (22 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 962 once invoked, about $0.0002 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
invarianteval
Before finalizing structured or extracted output in a domain with declared safety invariants, verify the output against your invariant suite and refuse to ship when a locked field was model-auto-filled. Invoke when the user or task involves high-stakes structured extraction, compliance fields, or pass/fail results…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
promptfoo-provider-setup
Configure promptfoo providers or redteam targets for hosted models, live HTTP APIs, Python/JavaScript local scripts, agent SDKs, or multi-input systems. Use when connecting promptfoo to the system under test, mapping vars, auth env vars, request bodies, response transforms, or static-code-derived provider wrappers. Do…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.