Borrowing it
Nothing to install: this file belongs to Eduardo-Salvador/Agent-Harness-Kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Eduardo-Salvador/Agent-Harness-Kit/main/.agents/skills/writing-plans/SKILL.mdgit clone --depth 1 https://github.com/Eduardo-Salvador/Agent-Harness-KitWrote 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/eduardo-salvador/agent-harness-kit/writing-plans)<a href="https://agentmods.dev/skills/eduardo-salvador/agent-harness-kit/writing-plans"><img src="https://agentmods.dev/badge/skills/eduardo-salvador/agent-harness-kit/writing-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/eduardo-salvador/agent-harness-kit/writing-plans"><img src="https://agentmods.dev/badge/skills/eduardo-salvador/agent-harness-kit/writing-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 | $0.00045 | $0.00542 |
| Opus 5.5 | $0.00018 | $0.00217 |
| Sonnet 5.5 | $0.00009 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
writing-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 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.
What it actually says
Writing plans
Before graph creation, apply the playbook's delegation assessment: inspect actual host capacity, identify worthwhile independent specialist outcomes, pin shared contracts, and assign exclusive write sets. Do not collapse independent workstreams into one broad node and then use the lack of ready nodes as a reason to work solo. Dispatch eligible branches through parallel-dispatch; otherwise record the concrete sequential reason inline. Keep trivial work lean and keep RED/GREEN with each implementation.
- Read
../../../harness/playbooks/writing-plans.mdbefore creating implementation nodes or task briefs. Run its mandatoryagent-harness preflightbefore decomposition and stop on missing declared prerequisites. - First apply the
direct-trivialgate in the playbook. If it passes, edit directly without loading planning artifacts, creating a SPEC/TASK, graphing, TDD, handoff, or review. Otherwise activate automatically after approved first-run discovery, approved feature discovery, or any later request that introduces non-trivial implementation work. The user may invoke this skill explicitly but does not need to. - Use a compact inline spec for bounded same-context work and a plan for larger work. Assign
assurance: none|light|fullindependently. Create TASK/handoff/review packets only for actual separate consumers. - Decompose planned work into ordered, independently checkable units targeting 15–30 minutes of active agent work each. Tool wait time and independent review are outside that target. Justify units outside the range by atomicity, runtime cost, or risk.
- Generate a self-contained
TASK.mdwhen a separate executor will consume it; a same-context inline node uses a compact inline spec and graph transition. Pin plan revision/step, outcome, owned paths, scoped context, non-goals, acceptance, verification, assurance, stop/replan triggers, andtest_strategy. Behavior changes and bug fixes keep focused RED/GREEN in the same unit. - Do not dispatch a non-simple task without an approved/ready plan and complete spec. Do not let the implementer choose product behavior, broaden scope, add dependencies, or improvise around missing decisions; it must stop, persist evidence, and request spec revision.
- Optimize planning context: use approved context/feature briefs and scoped source evidence, avoid broad rescans, do not duplicate prose across plan and task, and do not create a separate plan file for simple work.
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 Changed · +2 lines 62aba171ce6e
- 1mo ago Changed d6ff5bb1b1a6
- 1mo ago First seen · 15 lines · 45 tokens per session scan A 79d6b2737460
writing-plans is a skill published in the GitHub repository Eduardo-Salvador/Agent-Harness-Kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 542 once invoked, about $0.0002 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
forming-an-openrig-mental-model
Use when the system around you does not make sense yet: you just booted into a seat and do not know how the pieces fit; someone said rig, pod, seat, fleet, topology, or slice and you are not certain what they mean here; you are unsure what kind of rig you are in or what it is for; you do not know how skills reach you…
orienting-to-an-inherited-seat
Use when you have just been primed into an EXISTING seat through a planned handover — a different agent retired and handed you the seat plus its earned context — and you need a world model of what just happened to you. Covers how a handover differs from compaction and from a fresh launch, the…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
applying-a-permission-policy
Use before launching a team during agent-guided setup, or when a user asks to configure OpenRig command permissions, reduce repeated native approval prompts, or apply a selected rig/seat permission policy.
messaging-the-human
Use when project policy calls for a human decision or update, a human delivery is pending or failed, or a reply must resume the right work.
openrig-upgrade
Use when an agent is preparing or performing an OpenRig CLI/daemon upgrade and must preserve live seats, verify each mutation, or reconcile managed plugin and skill files without overwriting local work.