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.
git clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/commands/samibs/skillfoundry/delivery)<a href="https://agentmods.dev/commands/samibs/skillfoundry/delivery"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/delivery/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/commands/samibs/skillfoundry/delivery"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/delivery.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 | $0.00148 | $0.01028 |
| Opus 5.5 | $0.00059 | $0.00411 |
| Sonnet 5.5 | $0.00030 | $0.00206 |
| Haiku 4.5 | $0.00015 | $0.00103 |
Grade A, and why
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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/delivery — Delivery Efficiency
Canonical policy:
agents/_delivery-efficiency.md· Full docs:docs/DELIVERY-EFFICIENCY.md
Do not perform more engineering activity than is necessary to prove the requested change correct. A shorter execution is not automatically better. A longer execution is not automatically safer. The correct execution is the minimum defensible one.
Agent effectiveness = accepted useful change / (elapsed time × compute cost × human attention)
What it prevents
| Waste | How it is stopped |
|---|---|
| A typo fix triggering the repository-wide suite | LOW budget caps scope at smoke; full is unreachable from a budget alone |
| Re-running a check that already passed | Evidence keyed to the content hash of the files it depended on |
| Re-running one that already failed | FIX_FIRST — fix the cause, don't reproduce the failure |
| Three agents running the same suite | The first claims it; the others consume its evidence |
| Re-deriving the architecture every task | Shared mission facts, with confidence levels |
Escalating to full after fixing a test |
Escalation needs evidence of wider impact, not a passing fix |
| Re-reviewing an already-proven diff | DeliveryComplete is objective, and says what not to do next |
Before you implement
/delivery plan STORY-042 --text "<the task>" --base origin/main
Gives you, in one step: the delivery budget and why, the measured blast radius, the test
scope, and the reasoning behind it. Then follow /delivery policy <BUDGET> for the steps
that budget warrants.
Do not open with a repository-wide scan, build or test run to "get oriented." In a parallel wave that is the single largest source of wasted execution — the same scan, once per worker, proving nothing the shared context did not already hold.
Before any expensive validation
/delivery check --kind test --command "npm test -- src/auth" --files src/auth/token.ts
REUSE → skip it. FIX_FIRST → fix the cause. WAIT → another worker is running it.
RUN → it is genuinely needed and the claim is yours.
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.
- 1mo ago First seen · 101 lines · 148 tokens per session scan A 56aab01274f8
delivery is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 14d ago), licensed MIT. It adds 148 tokens to every session and 1,028 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-06.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.