Borrowing it
Nothing to install: this file belongs to seasonedcc/discord-manager. 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/seasonedcc/discord-manager/main/.claude/skills/self-improvement/SKILL.mdgit clone --depth 1 https://github.com/seasonedcc/discord-managerWrote 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/seasonedcc/discord-manager/self-improvement)<a href="https://agentmods.dev/skills/seasonedcc/discord-manager/self-improvement"><img src="https://agentmods.dev/badge/skills/seasonedcc/discord-manager/self-improvement/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/seasonedcc/discord-manager/self-improvement"><img src="https://agentmods.dev/badge/skills/seasonedcc/discord-manager/self-improvement.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 | $0.00072 | $0.01237 |
| Opus 5 | $0.00036 | $0.00619 |
| Sonnet 5 | $0.00014 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
self-improvement 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improvement
Everything here documents the repository as it is on main. If main disagrees with this file, main wins: follow it and flag the drift.
The last step of every task: mine what just happened for durable lessons and codify the ones that earn it. This is the most valuable and most dangerous part of the process — a good instruction improves every future session; a bad one biases every future session. Generalize with the big picture in mind, and codify only with conviction.
When to run
- After every other Definition of Done criterion has passed, before declaring the task done.
- For a multi-task effort, one pass over the whole arc when the effort concludes, with the full picture in view. Individual tasks inside such an effort skip the per-task pass — their lessons are mined at the end, never piecemeal.
- "No lessons worth codifying" is a valid and common outcome, especially for small tasks — state it explicitly and finish. Never manufacture a lesson to look productive.
Source ranking
Weigh evidence in this order:
- User instructions, corrections, and feedback — the highest signal, outranking everything else. Anything the user had to say twice is something the system failed to absorb the first time: a top-priority candidate. A lesson that contradicts a stated user preference is wrong, no matter how much other evidence supports it.
- Failures with a root cause — an incident traced to its mechanism. An untraced failure is not a lesson yet.
- Wins — patterns that demonstrably worked and would not be rediscovered cheaply.
Mine the real record, not memory: the session ledger, the conversation (the user's messages above all), per-lane artifacts, PR review threads.
Where each source lives:
- The session ledger — in the scratchpad directory listed in the system prompt.
- The full conversation — a JSONL transcript under the Claude config directory at
projects/<cwd with slashes replaced by dashes>/<session-id>.jsonl; the current session is the most recently modified file there, and compaction summaries cite the exact path. Long sessions grow to hundreds of megabytes — never read one wholesale. Extract layers with a script filtering by role: user messages and hook feedback first (highest signal, smallest volume), assistant narration only if needed, then slice for miners. - Per-lane artifacts — subagent transcripts live beside the session transcript; lane ledgers live in the scratchpad.
- PR review threads —
gh pr view <number> --commentsandgh api repos/<owner>/<repo>/pulls/<number>/comments.
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 · 69 lines · 72 tokens per session scan A a0fe8448b132
self-improvement is a skill published in the GitHub repository seasonedcc/discord-manager (3 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,237 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
psl-ast-layers
How to use the PSL syntax tree layers (green tree, red tree, strongly-typed AST classes) correctly. Use for any PSL-related work: PSL interpreters (contract-psl), helpers inside the psl-parser package, the language server, formatters, or anything else that consumes parse() output from @internal/psl-parser.
ast-visitor-pattern
Use the frozen-class/visitor pattern for discriminated unions that have multiple dispatch sites. Use when creating a new set of variants (commands, IR nodes, factory calls) that will be switched over in 2+ places, or when refactoring an existing union type that has grown multiple switch sites.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
bumping-biome
Bumps biome package versions (e.g. @biomejs/biome) using pnpm, aligns biome.jsonc files with the new version/s across the repository and runs biome-related checks. Use when required to update biome to a newer version - explicitly or implicitly (e.g. after running pnpm up, pnpm update, pnpm upgrade without specific…
dynamodb-toolbox-patterns
Provides TypeScript patterns for DynamoDB-Toolbox v2 including schema/table/entity modeling, .build() command workflow, query/scan access patterns, batch and transaction operations, and single-table design with computed keys. Use when implementing type-safe DynamoDB access layers with DynamoDB-Toolbox v2 in TypeScript…
azure-cosmos-ts
Data plane SDK for Azure Cosmos DB NoSQL API operations — CRUD on documents, queries, bulk operations.