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/threat-vector-security/guardian-agent/verification-before-completionnpx skills add Threat-Vector-Security/guardian-agent --skill verification-before-completiongit clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agentWrote 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/threat-vector-security/guardian-agent/verification-before-completion)<a href="https://agentmods.dev/skills/threat-vector-security/guardian-agent/verification-before-completion"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/verification-before-completion.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00543 |
| Opus 5 | $0.00014 | $0.00271 |
| Sonnet 5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
verification-before-completion 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 5d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Evidence before claims.
Do not say work is done, fixed, or passing until you have run the command or check that proves it.
Gate
Before making a completion claim:
- Identify the command or check that proves the claim.
- Run it fresh.
- Read the full result, including failures and exit status.
- State the actual outcome.
Completion requires the real proof surface to be green, not just a convenient subset.
Use the phrase full legitimate green as the bar:
- the relevant focused check passes
- any stronger existing regression, integration, or scenario check that proves the claim also passes
- no known broader required check is being skipped or silently weakened
In the written response, explicitly use the phrase proof surface when describing the completion bar.
Examples
- "Tests pass" requires the relevant test command output.
- "Build succeeds" requires the build command output.
- "Bug is fixed" requires the original reproduction or regression test to pass.
- "Requirements are met" requires checking the implemented result against the requested scope, not just passing tests.
- "Ready to hand off" requires the proof surface that actually matches the promised change, not a narrower substitute.
Red Flags
Stop if you are about to say:
- should be fixed
- looks good now
- probably passes
- done
without fresh verification evidence in the current turn.
Also stop if:
- you are skipping a broader existing check without explaining why
- you are replacing a failing real-world check with a weaker new test
- you are claiming success from partial green when the legitimate completion bar is still red
Repo-Specific Verification
When working in this GuardianAgent repository, prefer the existing harnesses before inventing ad hoc smoke checks:
scripts/run-code-ui-smoke.sh-> runsnode scripts/test-code-ui-smoke.mjsscripts/test-coding-assistant.mjs-> coding assistant and code-session workflow harnessscripts/run-skills-routing-harness.sh-> runsnode scripts/test-skills-routing-harness.mjs
What ships with it
4 files 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.
- 5d ago First seen · 74 lines · 27 tokens per session scan A 213054b0799d
verification-before-completion is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 543 once invoked, about $0.0001 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
orloj-generator
Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…
continuum-handoffs
Build agent-to-agent transitions with Continuum's Handoff system — triage routing, history summarization modes (FULL/SUMMARY/RECENTN/HYBRID), cycle detection, depth tracking, return-to-parent. Invoke when the user asks "route customer requests to specialists", "agent that can transfer to another", "summarize history…
continuum-llm-providers
Pick the right LLM provider, configure structured outputs, control context-window compression, and use the LLMClient directly. Provider routing is by model-string prefix; LiteLLM has been removed. Also covers Smart Gateway integration for multi-provider routing. Invoke when the user asks about "switch to Claude"…
continuum-temporal
Build durable agent workflows with Temporal — sequential/parallel/loop/conditional steps, human-in-the-loop approval gates, custom workflows and activities. Invoke when the user asks "long-running workflow", "approval gate", "human in the loop", "retry on failure", "workflow survives restart", or anything…
continuum-testing
Write tests for Continuum agents — mock LLM and memory clients via the DI Container, use fakeredis for sessions, snapshot agent responses, and run pytest-asyncio. Invoke when the user asks "test my agent", "mock the LLM", "fakeredis", "container injection", "pytest", or wants their CI to validate agent behavior…