A set of guarded ways to write long-term Dory memory through command-line, MCP, or HTTP interfaces. It supports previews, temporary inbox entries, targeted replacements, and controlled cleanup.

Use it to add, replace, or forget durable memory, route uncertain notes to an inbox, preview changes with a dry run, and safely remove verified scratch artifacts.

It reduces the risk of writing memory to the wrong place, overwriting existing information, or deleting the wrong test data. It requires searches, previews, and saved content hashes for sensitive replacements or deletions.

dory-write — Skill for Claude Code and Codex by deeflect/dory

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.

Any agent

npx skills add deeflect/dory --skill dory-write

Clone the repo

git clone --depth 1 https://github.com/deeflect/dory

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/deeflect/dory/dory-write/github.svg)](https://agentmods.dev/skills/deeflect/dory/dory-write)

Your own site

<a href="https://agentmods.dev/skills/deeflect/dory/dory-write"><img src="https://agentmods.dev/badge/skills/deeflect/dory/dory-write/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/deeflect/dory/dory-write"><img src="https://agentmods.dev/badge/skills/deeflect/dory/dory-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 418 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.00418
Opus 5.5	$0.00012	$0.00167
Sonnet 5.5	$0.00006	$0.00084
Haiku 4.5	$0.00003	$0.00042

Measured 1mo ago against content hash b1deae98cf85, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dory-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 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.

skills/dory-write/SKILL.md · 28 lines

What it actually says

Dory Write

Use Dory write surfaces through CLI/MCP/HTTP when durable memory should change.

Workflow:

Search first to see what already exists
Prefer semantic dory_memory_write / memory-write with action write, replace, or forget
Use dry_run=true first when the subject or target is not obvious
Use exact-path dory_write only through MCP/HTTP when the target path is known and you have read the current hash
Use dory_purge only for exact scratch/test artifact cleanup, and keep its default dry_run=true until the target/hash are verified

Rules:

Do not invent frontmatter
Do not create core/ files casually
Use force_inbox=true for tentative or scratch captures
Use allow_canonical=true only after preview when a semantic write intentionally resolves to canonical memory
Exact-path dory_write kinds are append, create, replace, and forget
New exact-path files require frontmatter.title and frontmatter.type; use type: capture for inbox/** and type: note only under references/notes/**
Exact-path replace and forget require expected_hash; forget also requires reason
CLI exposes semantic memory-write and guarded purge; exact-path dory_write is an MCP/HTTP surface, not a top-level CLI command
Legacy add/create write actions normalize to write; remove/delete normalize to forget, but new instructions should use the canonical action names
Plain-text mentions of known people/projects will create graph edges automatically; wikilinks are optional, not required

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.

1mo ago First seen · 28 lines · 31 tokens per session scan A b1deae98cf85

Subscribe to this mod's changes

dory-write is a skill published in the GitHub repository deeflect/dory (12 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 418 once invoked, about $0.0001 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 2026-08-30.

Claude Code Memory and context agents ai-agents codex docker fastapi

agentmemory-agents

How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.

rohitg00/agentmemory · 46 tokens

memory-retain

Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.

vectorize-io/hindsight · 46 tokens

last30Days

Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…

chaitanyagiri/munder-difflin · 83 tokens

thisWeek

Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…

chaitanyagiri/munder-difflin · 77 tokens

kb-research

Structured approach to finding and synthesizing information from the user's knowledge base.

MODSetter/SurfSense · 17 tokens

md-fetch-summarize

Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of ". Proactively suggest when the user pastes a URL and asks what it…

chaitanyagiri/munder-difflin · 93 tokens