predict

A forecasting capability that estimates a future state, value, or outcome from current information, past observations, and stated conditions. It includes confidence or probability, alternatives, and assumptions.

In plain words
What is it for?
Use it to forecast metrics, risks, system states, events, or release outcomes over a chosen time horizon.
Why use it?
It gives you an explicit projection instead of relying on an unrecorded guess. Listing assumptions and alternative outcomes makes uncertainty easier to assess.

Skill for Claude CodeCodex

Part of the agent-capability-standard plugin — 42 skills, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/synaptiai/agent-capability-standard/predict
Any agent
npx skills add synaptiai/agent-capability-standard --skill predict
Clone the repo
git clone --depth 1 https://github.com/synaptiai/agent-capability-standard

Made for: Claude Code, Codex.

Or install agent-capability-standard, the plugin that ships this one along with the rest of its 42 skills, 2 hooks.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,786 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.01786
Opus 5 $0.00015 $0.00893
Sonnet 5 $0.00006 $0.00357
Haiku 4.5 $0.00003 $0.00179

Measured 3d ago against content hash a44e44f891f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

predict 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 3d 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.

skills/predict/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intent

Forecast future states or outcomes for a target based on current state, historical patterns, and assumed conditions. This capability consolidates all forecasting tasks (risk, impact, time, etc.) into a single parameterized operation.

Success criteria:

  • Prediction for requested target and horizon provided
  • Probability or confidence assigned to prediction
  • Alternative outcomes considered
  • Assumptions explicitly stated

Compatible schemas:

  • schemas/output_schema.yaml

Inputs

Parameter Required Type Description
target Yes string What to predict (metric, state, outcome, event)
horizon No string Prediction timeframe (e.g., "1 week", "next release", "end of sprint")
conditions No object Assumed conditions for prediction
method No string Prediction approach (trend, model, heuristic)

Procedure

  1. Define prediction target: Clarify what outcome is being predicted

    • Specify the metric, state, or event to forecast
    • Establish the prediction horizon
    • Note any boundary conditions
  2. Gather historical data: Collect relevant past observations

    • Identify patterns and trends
    • Note data quality and coverage
    • Look for relevant precedents
  3. Establish conditions: Document assumptions about the future

    • Note what must remain constant
    • Identify key variables that could change
    • Consider external factors
  4. Generate prediction: Forecast the most likely outcome

    • Apply trend analysis or modeling
    • Calculate probability of primary prediction
    • Identify alternative outcomes
  5. Consider alternatives: Evaluate other possible outcomes

    • List plausible alternative scenarios
    • Assign rough probabilities to alternatives
    • Note what would cause each alternative
  6. Ground prediction: Document evidence and reasoning

    • Reference data supporting the prediction
    • Note the reasoning chain
    • Explicitly state all assumptions

Read the full file on GitHub · 237 lines

Files

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.

Changes

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.

  1. 3d ago First seen · 237 lines · 31 tokens per session scan A a44e44f891f7

Subscribe to this mod's changes

predict is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,786 once invoked, about $0.0002 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.