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.
npx skills add ankitkr3/compounded --skill using-compoundedgit clone --depth 1 https://github.com/ankitkr3/compoundedWrote 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/ankitkr3/compounded/using-compounded)<a href="https://agentmods.dev/skills/ankitkr3/compounded/using-compounded"><img src="https://agentmods.dev/badge/skills/ankitkr3/compounded/using-compounded/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/ankitkr3/compounded/using-compounded"><img src="https://agentmods.dev/badge/skills/ankitkr3/compounded/using-compounded.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 | $0.00073 | $0.01235 |
| Opus 5.5 | $0.00029 | $0.00494 |
| Sonnet 5.5 | $0.00015 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
using-compounded 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using compounded
compounded is installed. This means three things are true:
-
A user-global memory file lives at
~/.claude/compounded/USER.md. It is loaded into your context at session start. It is bounded — usually under 1500 characters. Use it for preferences and facts that apply across all the user's projects, not for project-specific notes (those belong in CLAUDE.md or AutoMemory's MEMORY.md). -
Skills you create earn trust over time. Skills do not start trusted. They start as proposals, get verified by replay, and graduate through a four-state trust ladder.
-
There is a portable archive. The user can run
/compounded:exportto bundle their USER.md and verified skills into a single archive that moves between machines.
The Trust Ladder
When you (the agent) discover a useful procedure during a session — something non-trivial, repeatable, that took you more than a couple of tool calls to figure out — you may propose it as a skill. Skills then graduate through four states:
| State | What it means | When it loads |
|---|---|---|
.proposed |
Just authored. Untested. | Never auto-loaded. Listed by /compounded:status. |
.verified |
Replayed successfully on at least one matching task. | Loads only when explicitly invoked by name. |
.trusted |
Used 3+ times without correction. | Auto-loads when relevant, asks for confirmation before applying. |
.autonomous |
Used 10+ times, zero corrections in last 5. | Auto-loads and applies without asking. |
Promotions happen automatically based on usage. Demotions also happen automatically:
- A user correction during a skill's use → demote one step
- 3 corrections in 30 days → demote to
.proposed - A failed verification on a
.proposedskill → move to.rejected/(recoverable, not deleted)
When to propose a skill
Use the compounded-author skill (which has the full procedure) when all of these are true:
- The task involved more than 3 tool calls
- The procedure is repeatable on a similar future task
- You actually solved it (not just gave up halfway)
- It is not redundant with an existing skill
- It does not duplicate something native (Claude Code's bundled skills, AutoMemory, AutoDream)
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 First seen · 84 lines · 73 tokens per session scan A 7cd071c5b595
using-compounded is a skill published in the GitHub repository ankitkr3/compounded (5 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 1,235 once invoked, about $0.0003 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
relay
A Chinese-language procedure for handing an unfinished task from one AI session to another without losing its context.
67-agency-vendor-brief-global
Use when briefing or managing an EXTERNAL agency, freelancer, or production vendor — scope of work, deliverable specs, revision rounds, approval process, USD payment milestones, IP assignment and confidentiality terms, communication rules, and a post-project vendor scorecard. Trigger on 'brief an agency', 'hire a…
token-check
Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.
knowledge-wiki
A tool that turns useful lessons from coding sessions into general articles for a team wiki. A wiki is a collection of linked reference pages, and this one can be kept locally or shared through a Git repository.
memory
Unified memory CRUD: write/update/delete/query file-based markdown entries and sync to MCP semantic store. TRIGGER when: saving a new memory entry, updating or deleting an existing entry, querying stored memories, or deduplicating before write. SKIP: 3-tier agent memory (use agent-memory); in-task vector recall (use…
semantic-memory-mcp
Proactive use of semantic-memory MCP tools (semanticsearch, semanticrecall). TRIGGER when: an agent should search vector memory for prior insights mid-task. SKIP: file-based 3-tier memory (use agent-memory); storing a new memory (use semantic-memory-store).