Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bnet47/codexiconnpx agentmods add skills/bnet47/codexicon/autonomous-buildWrote 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/bnet47/codexicon/autonomous-build)<a href="https://agentmods.dev/skills/bnet47/codexicon/autonomous-build"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/autonomous-build/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/skills/bnet47/codexicon/autonomous-build"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/autonomous-build.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 | $0.00020 | $0.02146 |
| Opus 5 | $0.00010 | $0.01073 |
| Sonnet 5 | $0.00004 | $0.00429 |
| Haiku 4.5 | $0.00002 | $0.00215 |
Grade A, and why
autonomous-build 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 today.
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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Build
Use Build for implementation requests. Work only in the current local checkout and active branch. Pure explanations and read-only reviews are exempt from this implementation workflow.
Contract
Read root SPEC.md before editing. For multi-task work, read root TASKS.md and validate both:
python scripts/codexicon.py spec-check
python scripts/codexicon.py tasks-next
If an authorized implementation has no TASKS.md, create the smallest validated
register from the root contract through $write-plan without a routine approval
stop. Use persisted states TODO, ACTIVE, BLOCKED, and DONE; queue outcomes
are READY, RESUME_ACTIVE, BLOCKED, COMPLETE, and INVALID.
Before every code generation or refactor, state the trace:
Trace: T-001 -> R-001 -> I-001
Reject or mark BLOCKED any task that cannot be traced to SPEC.md.
Decision visibility and scope gate
Record each consequential assumption or decision in the append-only journal at
agent_docs/decisions/ as a new ADR-NNN-short-title.md record. The record
must include the decision or assumption, rationale, alternatives considered,
impact, owner, date, status, and inspectable evidence. Never rewrite or delete
an accepted record; supersede it with a later record. The journal is guidance
and history, not a runtime or an authority grant.
A related correction may stay in the current task only when it is small,
reversible, directly related, and within the declared system boundary. Keep the
task trace, declared file boundary, and verification scope accurate. Otherwise
stop and explicitly escalate before editing if the change affects authority,
product behavior, schema or data shape, security posture, or an irreversible or
destructive outcome. Credentials, production actions, migrations, external
writes, publication, deployment, legal/compliance commitments, and material
architecture choices also require that escalation. $ship or the responsible
human owns those actions; a journal entry does not authorize them.
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.
- today Changed · +124 lines 000732df04a9
- yesterday Changed · +10 lines 0caebcae9b35
- 3d ago First seen · 48 lines · 20 tokens per session scan A 6d6552a9faaf
autonomous-build is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 2,146 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 2026-09-09.
Other skills, from other repositories
qa
Run scalable, isolated live QA for nac development. The top-level local orchestrator must parse n (default 4), dispatch one setup worker with this skill, copy its n assignment contracts verbatim into exactly n parallel test workers with this skill, then dispatch one aggregate worker with this skill using all test…
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".
testgen-flow
Workflow for generating test cases from requirements (Issue Tracker / Wiki sources), exporting to a Test Management System, etc.
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
ring:implementing-tasks
Implementing a single planned task (Task N.M.T) end-to-end: selects the right backend agent by language and service type, drives one TDD RED->GREEN turn, then verifies coverage, lint, license headers, runtime, and delivery before handoff. Runs as Gate 0 before ring:reviewing-code. Use to drive ONE task inside an…
ring:validating-acceptance-criteria
Validating a completed task against its acceptance criteria, mapping each AC to evidence, and gating completion on explicit user sign-off (self-approval prohibited). Gate 5 of ring:running-dev-cycle / ring:running-dev-cycle-frontend, run at task cadence after ring:reviewing-code. Use when implementation and tests are…