learn-pending

A command for listing learning changes that are waiting for approval. These changes can propose new skills or stored memory claims.

In plain words
What is it for?
Use it to inspect pending files, their type, action, reason, and creation time, then see how to approve or reject them.
Why use it?
It shows what has been proposed without applying anything, so you can review pending changes before they affect future work.

Command

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 commands/fmflurry/settings-opencode/learn-pending
Clone the repo
git clone --depth 1 https://github.com/fmflurry/settings-opencode
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 349 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 $0.00007 $0.00349
Opus 5 $0.00003 $0.00175
Sonnet 5 $0.00001 $0.00070
Haiku 4.5 $0.00001 $0.00035

Measured 2d ago against content hash 467f4245c304, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-pending 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 2d 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.

commands/learn-pending.md · 45 lines

What it actually says

Learn Pending

List all staged learning changes awaiting approval: $ARGUMENTS

Your Task

  1. List all files in ~/.config/opencode/pending/skills/ and ~/.config/opencode/pending/memory/
  2. For each file, parse the JSON and display:
    • ID: filename (without extension)
    • Type: skill or memory
    • Action: create or patch
    • Reason: the stated reason for the change
    • Timestamp: when it was created
  3. At the end, show:
    • Total pending count
    • Instructions for approving/rejecting

Output Format

## Pending Learning Changes

### Skills (/pending/skills/)
| ID | Action | Reason | Created |
|----|--------|--------|---------|
| 1712345678-mistral-pattern | create | Mistral models need explicit tool reminders | 2026-04-05 14:32 |

### Memories (/pending/memory/)
| ID | Subject | Predicate | Object | Created |
|----|---------|-----------|--------|---------|
| 1712345680-react-18 | project | uses | React 18 | 2026-04-05 14:35 |

**Total: 2 pending**

### Usage
- `/learn-approve <id>` — Approve and apply a pending change
- `/learn-reject <id>` — Reject and delete a pending change
- `/learn-review` — Manually trigger a learning review of the current session
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. 2d ago First seen · 45 lines · 7 tokens per session scan A 467f4245c304

Subscribe to this mod's changes

learn-pending is a command published in the GitHub repository fmflurry/settings-opencode (172 stars, last pushed 20d ago), licensed MIT. It adds 7 tokens to every session and 349 once invoked, about $0.0000 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 2026-08-30.