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/agent-sh/agentsys/validate-deliverynpx skills add agent-sh/agentsys --skill validate-deliverygit clone --depth 1 https://github.com/agent-sh/agentsysWrote 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/agent-sh/agentsys/validate-delivery)<a href="https://agentmods.dev/skills/agent-sh/agentsys/validate-delivery"><img src="https://agentmods.dev/badge/skills/agent-sh/agentsys/validate-delivery.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 | $0.00036 | $0.01239 |
| Opus 5 | $0.00018 | $0.00620 |
| Sonnet 5 | $0.00007 | $0.00248 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
validate-delivery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
validate-delivery
Autonomously validate that a task is complete and ready to ship.
Validation Checks
Check 1: Review Status
function checkReviewStatus(reviewResults) {
if (!reviewResults) return { passed: false, reason: 'No review results' };
if (reviewResults.approved) return { passed: true };
if (reviewResults.override) return { passed: true, override: true };
return { passed: false, reason: 'Review not approved' };
}
Check 2: Tests Pass
# Detect test runner and run
if grep -q '"test"' package.json; then
npm test; TEST_EXIT_CODE=$?
elif [ -f "pytest.ini" ]; then
pytest; TEST_EXIT_CODE=$?
elif [ -f "Cargo.toml" ]; then
cargo test; TEST_EXIT_CODE=$?
elif [ -f "go.mod" ]; then
go test ./...; TEST_EXIT_CODE=$?
else
TEST_EXIT_CODE=0 # No tests
fi
Check 3: Build Passes
if grep -q '"build"' package.json; then
npm run build; BUILD_EXIT_CODE=$?
elif [ -f "Cargo.toml" ]; then
cargo build --release; BUILD_EXIT_CODE=$?
elif [ -f "go.mod" ]; then
go build ./...; BUILD_EXIT_CODE=$?
else
BUILD_EXIT_CODE=0 # No build step
fi
Check 4: Requirements Met
async function checkRequirementsMet(task, changedFiles) {
const requirements = extractRequirements(task.description);
const results = [];
for (const req of requirements) {
const implemented = await verifyRequirement(req, changedFiles);
results.push({ requirement: req, implemented });
}
return {
passed: results.every(r => r.implemented),
requirements: results
};
}
function extractRequirements(description) {
const reqs = [];
// Extract bullet points: - Item
const bullets = description.match(/^[-*]\s+(.+)$/gm);
if (bullets) reqs.push(...bullets.map(m => m.replace(/^[-*]\s+/, '')));
// Extract numbered items: 1. Item
const numbered = description.match(/^\d+\.\s+(.+)$/gm);
if (numbered) reqs.push(...numbered.map(m => m.replace(/^\d+\.\s+/, '')));
return [...new Set(reqs)].slice(0, 10);
}
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.
- 4d ago First seen · 187 lines · 36 tokens per session scan A 55ead8019821
validate-delivery is a skill published in the GitHub repository agent-sh/agentsys (982 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 1,239 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
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…