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 skills add tolgakisaogullari/SumelaOS --skill executing-plansgit clone --depth 1 https://github.com/tolgakisaogullari/SumelaOSWrote 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/tolgakisaogullari/sumelaos/executing-plans)<a href="https://agentmods.dev/skills/tolgakisaogullari/sumelaos/executing-plans"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/executing-plans/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/tolgakisaogullari/sumelaos/executing-plans"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/executing-plans.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 | $0.00025 | $0.01253 |
| Opus 5 | $0.00013 | $0.00626 |
| Sonnet 5 | $0.00005 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade A, and why
executing-plans 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
-
PREPARATION:
- Invoke
using-git-worktreesto set up an isolated workspace. NEVER start implementation on the main/master branch without explicit user consent. - If the IDE supports subagent dispatch, STOP before executing and tell the user that
subagent-driven-developmentis preferred for quality, context isolation, and staged review gates. Continue with this skill only if the user explicitly chooses inline execution.
- Invoke
-
PLAN REVIEW & CONTEXT LOADING:
- Read the implementation plan (
docs/second-brain/artifacts/plans/...). - Review the plan critically before executing. Identify unclear instructions, missing files, unsafe assumptions, impossible verification steps, scope gaps, or conflicts with Second Brain state.
- Note the TDD Mode (Enabled or Skipped) from the header.
- Note the Security Constraints. Read
.sumela/skills/secure-coding-standard/SKILL.mdif not already in context — it applies to ALL implementation code, not only plans with an explicit security surface. - PHASE RULE SYNC: This skill activates the
implementationphase. Per.sumela/RULE_REGISTRY.md<phase_to_rule_matrix>, confirm every universal rule, every implementation-phase rule, and every rule matching the active stack scope(s) and domain(s) is loaded — READ any missing rule file now. If the registry file is missing, tell the user to run setup — do not guess the matrix. - If there are gaps, ambiguities, or concerns, STOP and ask the user. If clear, initialize a Todo/Checklist.
- REVIEW MODE OPT-IN (ask ONCE, before the first task — STOP and wait):
"How do you want task boundaries handled?
- Checkpoint mode (recommended): I stop after every task with a summary and wait for your approval before continuing.
- Flow mode: Tasks run back-to-back with concise progress notes and no stops; the mandatory comprehensive review (
requesting-code-review, Step 4) covers everything at the end." Record the choice; the user may switch modes at any task boundary. NEVER assume Flow mode silently — no clear answer means Checkpoint mode.
- Read the implementation plan (
-
EXECUTION (NO COMMITS ALLOWED): For each task sequentially:
- Mark the task
in_progress. - Execute exactly as written, adapting to the TDD Mode:
- If TDD is Enabled: follow strict Red-Green-Refactor.
- If TDD is Skipped: write implementation directly, but security-boundary changes still require automated validation.
- Actively apply
secure-coding-standardprinciples during all coding. - Run required verifications and tests for the task.
- Stage successful changes only when the active workflow or user explicitly expects staged output. If staging, use
git add <exact-file-path>only. - CRITICAL: DO NOT use
git commitduring this phase. The review agent must see the full uncommitted diff. - Mark the task
completed. - TASK BOUNDARY (per the Step 2 review-mode choice):
- Checkpoint mode: STOP after each task. Summarize what changed, verification run, staged/unstaged state, and the next task. Ask the user whether to continue, prepare a handoff prompt, or pause. Do not auto-advance.
- Flow mode: Give a one-line progress note (task name, files touched, verification result) and continue to the next task without stopping. Plan
## Checkpoint:blocks: run their verifications, but do not stop unless one fails. STILL STOP if: a verification fails, the plan is ambiguous, or the task touched an auth/security boundary — Flow mode never overrides the NO GUESSING constraint.
- Mark the task
-
MANDATORY CODE REVIEW PREPARATION & DISPATCH:
- After the final task is complete, invoke
requesting-code-review— in Checkpoint mode after the user approves moving to review; in Flow mode immediately, without waiting for approval (the user opted into exactly this). - When preparing the payload for the review subagent, explicitly detail the security mitigations applied in
{DESCRIPTION}. - Ensure
{SECURITY_MANDATE}instructs the reviewer to enforcesecure-coding-standard. - Wait for the code reviewer to inspect the uncommitted changes and provide feedback. Apply fixes via
receiving-code-review, then stage fixes only when the active workflow expects staged output.
- After the final task is complete, invoke
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 · 59 lines · 25 tokens per session scan A 470e549f63aa
executing-plans is a skill published in the GitHub repository tolgakisaogullari/SumelaOS (4 stars, last pushed 14d ago), licensed MIT. It adds 25 tokens to every session and 1,253 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 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.