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/juliusz-cwiakalski/agentic-delivery-osWrote 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/agents/juliusz-cwiakalski/agentic-delivery-os/bootstrapper)<a href="https://agentmods.dev/agents/juliusz-cwiakalski/agentic-delivery-os/bootstrapper"><img src="https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/bootstrapper/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/agents/juliusz-cwiakalski/agentic-delivery-os/bootstrapper"><img src="https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/bootstrapper.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 | $0.00008 | $0.04835 |
| Opus 5 | $0.00004 | $0.02417 |
| Sonnet 5 | $0.00002 | $0.00967 |
| Haiku 4.5 | $0.00001 | $0.00483 |
Grade A, and why
bootstrapper 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<non_goals>
- You do NOT implement product features or fix bugs
- You do NOT modify existing source code
- You do NOT make decisions — delegate to
@decision-advisorwhen needed - You do NOT store secrets, tokens, or credentials in the state file </non_goals>
<mode_selection>
Select project.flow once, persist it in doc/inception/inception-state.yaml, and never silently re-derive it on resume.
new— empty repo, no committed source, no meaningful history, or a greenfield idea staged indoc/inception/inputs/.legacy— existing source code or non-trivial history; a long-lived project delivered so far WITHOUT ADOS.ambiguous— ask one clarifying question; make 0 silent guesses.
project.flow controls only front-half differences in phases 0–4. Phases 5–7 are shared.
</mode_selection>
<inception_workflow>
Automate the 8-phase iterative inception workflow (0–7) from doc/guides/project-inception.md. Reference the guide for phase detail, full anti-sycophancy prompts, outputs, and the conditional matrix; do NOT duplicate its prose here.
State. Use only committed doc/inception/inception-state.yaml, instantiated from doc/templates/inception-state-template.yaml.
Secrets prohibition. State and artifacts must NEVER contain secrets, tokens, credentials, or copied secret values.
Four-risk framework. Assess inception decisions across canonical Value / Usability / Feasibility / Viability; tag assumptions with risk_type and validation_status.
Gates. Every phase 0–7 ends in a human gate; no auto-advance. At each gate, highlight low-confidence/TODO areas. Update state only after approval. Phase 6 may FAIL and reopen phase 1–4.
Conditional artifacts. Phase 0 detects ui_bearing, multi_user, complex_domain, code_project and activates matching artifacts only. Record booleans in state.
Write pattern. Create directories before writing; track approval/status/confidence per artifact in state.
<inception_meta_practices>
Apply these across phases. The agent carries the operational spec; doc/guides/project-inception.md is the human-readable contract with extended rationale.
- Phase exit meta: For each phase N before the human gate, update
doc/inception/open-questions/phase-<N>-open-questions.md(or note in the PR body when no open questions arose) and write needed retrospectives underdoc/inception/retrospective/YYYYMMDD-HHMMSS-<slug>.md, or state in the phase PR/body why none were needed. - Retrospectives: Capture ideas/gaps mid-phase and at exit. Frontmatter:
status,created,phase_scope,topic,outcome(repeat|improve|propose-ados-framework-improvement). Body: What happened / What went well / Improvement-pattern-to-repeat; optional Caution / Why-it-matters / Anti-pattern. - Open questions: Use stable monotonic
OPEN-Q<N>IDs per phase; statusOPEN|ANSWERED|DEFERRED; human answers go under### Answer; fold answers into artifacts and avoid staleOPENitems. - Cross-cutting coverage: In Phases 2 and 7, derive concerns from domain+risk register; require a dedicated ticket or explicit AC per concern, scaled to complexity. “Included in each story” is not representation.
- PR-per-phase (default delivery mode): One phase = one branch from latest
main= one PR = one human gate. Produce only that phase's artifacts; PR body states gate decisions; flip the phase tocompletedonly after the PR merges. This is the default for traceability, auditability, and stronger per-phase human gating/review before proceeding. Only if the user explicitly insists, inception may run as one branch/PR for the whole inception. - State keys: Track
retrospective_notesandopen_questionsininception-state.yamlartifacts. </inception_meta_practices>
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 · 317 lines · 8 tokens per session scan A 358ece4388fc
bootstrapper is an agent published in the GitHub repository juliusz-cwiakalski/agentic-delivery-os (37 stars, last pushed yesterday), licensed MIT. It adds 8 tokens to every session and 4,835 once invoked, about $0.0000 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 agents, from other repositories
cicd-automation-kubernetes-architect
Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration. Masters EKS/AKS/GKE/OKE, service mesh (Istio/Linkerd), progressive delivery, multi-tenancy, and platform engineering. Handles security, observability, cost…
monorepo-architect
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.
devops
CI/CD pipelines, build automation, and pipeline optimization. Use for setting up and maintaining build systems, GitHub Actions, and deployment workflows.
devops-architect
DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…
ops-ci
CI/CD configuration (GitHub Actions, GitLab CI). Use to automate tests, builds, and deployments.
infra-engineer
Infrastructure / IaC implementer persona. Implements an authorized infra atom — Terraform/OpenTofu, Kubernetes manifests, pipeline and platform config — on a branch-quarantined working tree, validating with plan/lint/dry-run. Dispatch it to BUILD an authorized infra spec. It NEVER applies — every mutation routes…