compress

A guide for shortening text and context while keeping the important information.

In plain words
What is it for?
Use it when a conversation is becoming too long or when you need a compact version of instructions, notes, or project context.
Why use it?
It removes repetition and filler so the remaining instructions or conversation are easier to scan and fit into less space.

Skill for Claude CodeCodex

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/xcota/pos/compress
Any agent
npx skills add xcota/pos --skill compress
Clone the repo
git clone --depth 1 https://github.com/xcota/pos

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 659 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 $0.00022 $0.00659
Opus 5 $0.00011 $0.00329
Sonnet 5 $0.00004 $0.00132
Haiku 4.5 $0.00002 $0.00066

Measured 3d ago against content hash 3b75873cfee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compress 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.

.claude/skills/compress/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

InfoCompressor — Context Compression

Compress text/context to ~30% of the original. Apply ALL 5 techniques simultaneously.

Techniques

1. Structural

  • Prose → tables (when data has patterns)
  • Paragraphs → bullet points (3-7 words each)
  • Nested → flat with for hierarchy

2. Linguistic

  • Kill filler: "it should be noted that" → cut
  • Kill hedging: "perhaps", "it seems" → cut
  • Active voice: "was done by X" → "X did"
  • Imperative mood: "you should run" → "run"
  • Present tense everywhere
  • Drop articles where meaning is clear

3. Symbolic

  • causality ("X causes Y" → "X → Y")
  • | alternatives ("either A or B" → "A | B")
  • + additions
  • = equivalence
  • ✓/✗ yes/no
  • ~ approximation

4. Abbreviation

Standard: cfg, env, srv, dir, repo, fn, arg, param, cmd, msg, req, res NEVER abbreviate: file paths, entity names, error messages, URLs, numbers

5. Deduplication

  • Each fact stated ONCE
  • Merge related items into a single statement
  • Remove repeated context from multiple messages

Modes

/compress context

Compress the current conversation. Output a compressed blob for a new session. Steps: review the full conversation → extract goals/decisions/progress/pending/files → apply all techniques → output a <2KB blob → show the ratio.

/compress clipboard

User pastes text. Return the compressed version.

/compress file <path>

Read the file, compress, return.

Quality Check

After compression verify:

  • All file paths preserved exactly
  • All numeric values preserved
  • All entity/variable names preserved
  • Meaning recoverable by someone who didn't read the original
  • No ambiguity introduced by abbreviation

Auto-Trigger (advisory)

Context-fill % isn't directly observable — gate on the token budget in CLAUDE.md instead. As the main thread approaches the 100K ceiling (or /session-save is invoked) → compress first → handoff blob. When context is clearly heavy (near the ~150K session-save threshold) → compress + save immediately → REFUSE further execution → handoff blob.

Read the full file on GitHub · 77 lines

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 · 77 lines · 22 tokens per session scan A 3b75873cfee0

Subscribe to this mod's changes

compress is a skill published in the GitHub repository xcota/pos (43 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 659 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

ori-memory

Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.

aayoawoyemi/Ori-Mnemos · 54 tokens

rtg-knowledge-graph-mcp

Operate the Vellis RTG Knowledge Graph MCP server for agent-driven graph work. Use when an agent has RTG MCP tools such as rtgvalidategraph, rtgapplylivegraphchanges, rtgstageknowledgechanges, rtgapplymigrationcutover, rtgexecutequery, snapshots, or ledger replay, especially for schema evolution, validation recovery…

volantlabs/vellis · 87 tokens

documentation-sync

Keep human documentation synchronized with canonical SysML v2 models, generated component and application views, implementation realizations, repository tooling, skills, and workflow rules. Use after model, code, generated-view, README, AGENTS, skill, command, or public behavior changes.

volantlabs/vellis · 57 tokens

python-component-implementation

Implement, review, or revise Python realizations of components from accepted textual SysML v2 contracts and generated views. Use when creating or aligning Python protocols, component classes, reference implementations, implementation bindings, or black-box contract tests.

volantlabs/vellis · 51 tokens

sysml-reference

Ground textual SysML v2 and KerML authoring, review, language-semantics decisions, construct selection, and official-validator diagnosis in the repository's checksum-pinned specification corpus. Use for questions or changes involving parts, references, features, actions, bindings, successions, flows, ports…

volantlabs/vellis · 92 tokens

model-hygiene-review

Audit accepted SysML v2 component or application models against implementations, protocols, consumers, tests, generated evidence, predecessor contracts, and git history before proposing remediation. Use for periodic model hygiene, suspected model/implementation drift, migration-loss reviews, verification-closure…

volantlabs/vellis · 72 tokens