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/romainsimon/skills-for-decision-makingnpx agentmods add skills/romainsimon/skills-for-decision-making/planning-horizonsWrote 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/romainsimon/skills-for-decision-making/planning-horizons)<a href="https://agentmods.dev/skills/romainsimon/skills-for-decision-making/planning-horizons"><img src="https://agentmods.dev/badge/skills/romainsimon/skills-for-decision-making/planning-horizons/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/romainsimon/skills-for-decision-making/planning-horizons"><img src="https://agentmods.dev/badge/skills/romainsimon/skills-for-decision-making/planning-horizons.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 | $0.00087 | $0.01781 |
| Opus 5 | $0.00044 | $0.00890 |
| Sonnet 5 | $0.00017 | $0.00356 |
| Haiku 4.5 | $0.00009 | $0.00178 |
Grade A, and why
planning-horizons 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 12d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning horizons
Two chronic errors in roadmapping, and both are cheap to fix:
- Planning deeper than the decision requires. Past a certain depth, extra planning changes nothing about what you do on Monday. That work is spend, not rigour.
- Leaving the discount rate implicit. Every argument about short-term versus long-term is an argument about a discount factor that nobody has written down. Write it down and the argument usually resolves in a minute.
The organising principle is receding horizon planning: plan to depth d, execute the first step, then replan. You are not committing to the plan. You are using the plan to choose the next action.
Workflow
- [ ] 1. Set the discount factor from a half-life you can defend
- [ ] 2. Find the depth where extra planning stops changing the first move
- [ ] 3. Prune the backlog against the incumbent
- [ ] 4. Evaluate the current plan before replacing it
- [ ] 5. Plan to that depth, commit only the first step, set a replan trigger
1. Set the discount factor
Do not argue about gamma. Argue about the half-life: how many periods until a payoff is worth half as much to us? Then convert.
node scripts/calc.js discount --half-life 6
That reports the effective horizon (1/(1-gamma)) - the point past which contributions
are noise - and the weight on payoffs at 1, 3, 6, 12 and 24 periods.
Defensible half-lives depend on your position, not your temperament:
| Position | Monthly half-life | Effective horizon |
|---|---|---|
| Under 6 months of runway | 3 | ~4 months |
| Profitable, stable | 12 | ~17 months |
| Funded with a clear multi-year thesis | 24 | ~35 months |
Runway is the honest driver. A short runway should produce a high discount rate, because a payoff after you run out of money has a utility of zero. That is not short-termism, it is arithmetic. Say it that way and the strategic argument becomes a financing argument, which is the one actually worth having.
2. Find the depth that matters
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 174 lines · 87 tokens per session scan A 494f783e7382
planning-horizons is a skill published in the GitHub repository romainsimon/skills-for-decision-making (11 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 1,781 once invoked, about $0.0004 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
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
architecture-aware-init
Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.