write

A helper that saves useful knowledge from a conversation as Markdown files under `.wisci/context/`. It tracks when saved information may become outdated.

In plain words
What is it for?
Use it to preserve reusable research findings, decisions, and architecture notes for future sessions. It is for durable knowledge, not temporary task progress.
Why use it?
Important research, decisions, and design notes can otherwise vanish when a session ends or its context is shortened.

Skill for Claude CodeCodex

Part of the wisci plugin — 5 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/ph3on1x/wisci/write
Any agent
npx skills add ph3on1x/wisci --skill write
Clone the repo
git clone --depth 1 https://github.com/ph3on1x/wisci

Made for: Claude Code, Codex.

Or install wisci, the plugin that ships this one along with the rest of its 5 skills, 2 hooks.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 784 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 $0.00050 $0.00784
Opus 5 $0.00025 $0.00392
Sonnet 5 $0.00010 $0.00157
Haiku 4.5 $0.00005 $0.00078

Measured 2d ago against content hash 8c4763187545, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/wisci.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/write/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/write — Context Externalizer

Move knowledge from the context window into a structured, persistent file in .wisci/context/. This is the "save to disk" operation — preserve what would otherwise be lost to context limits or session endings.

Boundary: /write stores reusable knowledge (research, decisions, architecture notes). Session work state (goal, in-progress, next steps) belongs in /compress.

Timestamp: !date '+%Y-%m-%d %H:%M'

Execution Flow

  1. Parse arguments. Read $ARGUMENTS to determine what to externalize from the current context.

  2. Derive topic slug. Extract the core topic noun phrase (strip filler: "results on", "notes about"), kebab-case, lowercase, max 5 words. If the user names a target file explicitly, use it.

  3. Check for existing file. Glob .wisci/context/ for the slug:

    • No match: Create Mode below.
    • Exact match, same topic: Merge Mode — read and follow references/merge-procedure.md.
    • Exact match, different topic: ask the user — merge or disambiguated new name.
  4. Write to .wisci/context/<topic-slug>.md (create directories as needed).

  5. Confirm. Report path, created vs merged, and a one-line content summary.

Create Mode

  1. Extract and structure the information from the current context per $ARGUMENTS
  2. Organize into logical ## sections
  3. Build a ## References section listing every file path mentioned in the content
  4. Write using the output format below

Output Format

# <Title inferred from arguments>

> Last updated by /write on <timestamp from above>
> Source: <what session context this was extracted from>

## Summary
<2-3 sentence overview>

## <Section 1>
<Structured content with all specifics preserved>

## Key Details
- **Decisions**: <every decision made, with rationale>
- **Open questions**: <anything unresolved>

## References
- `src/auth/middleware.ts` — auth middleware, token validation logic
- `src/auth/session.ts:42` — session expiry configuration

Read the full file on GitHub · 81 lines

Files

What ships with it

2 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. 2d ago First seen · 81 lines · 50 tokens per session scan A 8c4763187545

Subscribe to this mod's changes

write is a skill published in the GitHub repository ph3on1x/wisci (1 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 784 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

contorium-workspace-memory

Use Contorium workspace memory layers (focus, session events, Git, export) when resuming AI work or avoiding repeated project explanation.

ContoriumLabs/contorium · 33 tokens

apm-review-panel

Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in…

microsoft/apm · 178 tokens

apm-issue-autopilot

Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…

microsoft/apm · 238 tokens

apm-spec-guardian

Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/.schema.json), or the conformance fixture seed…

microsoft/apm · 215 tokens

apm-triage-panel

Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.

microsoft/apm · 59 tokens

cli-logging-ux

Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (richsuccess, richwarning, richerror, richinfo, richecho), DiagnosticCollector, STATUSSYMBOLS, CommandLogger, or any…

microsoft/apm · 94 tokens