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/execute-planWrote 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/execute-plan)<a href="https://agentmods.dev/skills/bnet47/codexicon/execute-plan"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/execute-plan/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/execute-plan"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/execute-plan.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 | $0.00021 | $0.00841 |
| Opus 5.5 | $0.00008 | $0.00336 |
| Sonnet 5.5 | $0.00004 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
execute-plan 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 24d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute a durable plan through autonomous-build
Announce: "I'm using execute-plan to implement the durable plan locally with bounded read-only review where it helps."
1. Load and validate the plan
Read the selected plan, linked root SPEC.md, and root TASKS.md. SPEC.md and TASKS.md are authoritative; the plan is context and decomposition, not a second execution engine. A plan produced for the current implementation request is authorized by that request; do not create an extra approval gate unless it exposes a consequential product or architecture choice. Preserve existing user changes without invoking Git. Confirm task paths and dependencies remain accurate, then run python scripts/codexicon.py spec-check and python scripts/codexicon.py tasks-next --json.
If resuming, run python scripts/codexicon.py resume, then verify the selected checkpoint against the plan and declared changed-path evidence. .codex-state/ is local verification state, not project memory.
2. Adapt into the shared Build loop
- Continue with the
$autonomous-buildloop: selectRESUME_ACTIVEbeforeREADY, execute only runnable tasks, verify each task, review meaningful risk, and persist evidence before marking itDONE. Do not create a separate plan-specific state machine or completion rule. - Build has one writer in the shared checkout: the primary agent by default. An explicitly chosen
implementermay write one bounded task sequentially; the primary agent re-reads the changed paths and owns integration and final verification. Never run concurrent writers. - Use
$engineering-looponly for independent read-only research or review, not as a parallel implementation lane.
Each explicitly delegated implementation brief must include the exact task text, global constraints, allowed files, dependency state, verification command, and side-effect authorization. Do not rely on hidden parent context.
When routing is enabled, the brief is also the minimum-sufficient dispatch
envelope: include the requirement/interface trace, acceptance rubric, risk and
review signals, escalation rule, and max_depth = 1. A worker cannot broaden
the paths or authority, spawn a child, or self-accept; requested/configured
routing is not observed runtime evidence unless the client exposes it.
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.
- 24d ago Changed · +5 lines 95dcf8567a8a
- 1mo ago Changed fb5aa36ff604
- 1mo ago Changed · -2 lines 7c32c4becae5
- 1mo ago Changed · -6 tokens per session 1506f6afa073
- 1mo ago First seen · 52 lines · 27 tokens per session scan A 17ff12ff4c10
execute-plan is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 20d ago), licensed MIT. It adds 21 tokens to every session and 841 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…
oma-scholar
Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.