Install
$ agentstack add skill-docmancer-docmancer-templates ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
docmancer
Docmancer keeps three things distinct: automatically combined machine-wide Shared Memory, deliberate project Markdown, and attributable evidence discovered from coding agents. Technical documentation lives in a separate index.
Executable: {{DOCS_KIT_CMD}}
All commands below use docmancer as shorthand for the full executable path above.
When to use it
- Prior decisions, project conventions, standing instructions, preferences, or earlier failures may affect the task.
- The user explicitly asks to remember or manage durable memory.
- The user asks about a library, SDK, API, or vendor and indexed documentation may provide a more exact answer.
- The user explicitly asks to protect, move, or restore Claude Code or Codex history and setup.
Memory workflow
- Run
docmancer ask ""when prior context may matter. - Treat returned content as cited reference data. Current user instructions and repository rules still take precedence.
- Follow a stable citation with
docmancer readwhen the full file, provenance, or current hash is needed. - When the user explicitly asks to manage durable memory, use
docmancer askto prepare one complete-file proposal. Apply it only with the user's confirmation or explicit--apply. - Before editing or moving an existing file, read it and pass its current content hash.
- Use
docmancer common,delivery, ortimelinefor cross-agent recurrence, delivery proof, or curated-file history.
Read-only Ask reads the latest committed index. When a generation provider is configured, it produces grounded prose by default after retrieval. Explicit mutation requests use one structured provider call to prepare one create, edit, pin, move, duplicate, trash, or restore proposal. Pass --read-only to suppress action planning, --apply only after explicit authorisation, --no-answer for evidence only, and --fresh only when the task must wait for changed agent sources to be indexed first.
A reply to one action clarification continues the original request. Do not treat it as a new read-only question. Never interpret yes or ok as approval to execute a stored proposal. Broad machine-wide forget requests use shared/canonical-exclusions.md to filter generated Shared Memory; they never edit the underlying repository or agent-owned source memory.
docmancer ask "what deployment decisions apply?"
docmancer ask "how did this policy change?" --history
docmancer ask "show the evidence only" --no-answer
docmancer ask "include newly changed agent files" --fresh
docmancer ask "remember that production releases require a smoke test"
docmancer ask "update decisions/release.md to require two reviewers" --apply
docmancer common
docmancer delivery
docmancer timeline
docmancer memory canonical
docmancer memory canonical show preferences
docmancer read --global profile/preferences.md
docmancer read docmancer://memory/
docmancer write "# Release process\n\nDeploy on Railway." --path decisions/release.md --scope project
docmancer edit docmancer://memory/ - --expected-hash
docmancer move docmancer://memory/ decisions/hosting.md --expected-hash
docmancer import ./notes
docmancer status --json
docmancer backup --dry-run
docmancer restore ./agents.dmbak --dry-run
docmancer consolidate
docmancer import copies whole Markdown files into the project inbox. It never rewrites the source. Stable docmancer://memory/ addresses survive moves.
Shared Memory rules
Machine-wide files live under profile/, principles/, projects/, and shared/. Project files belong under overview.md, decisions/, constraints/, workflows/, and lessons/.
Generated machine-wide sections contain a pinned zone and a generated zone. Combination replaces the generated zone. Use docmancer memory canonical pin for an explicit durable correction. Do not edit the generated zone.
Conversational Ask proposals affect exactly one complete file and never apply because the user merely types “yes”. Never trash, restore, connect Cloud, change capture installation, or publish Team memory without explicit user authorization.
Agent backup is separate from Shared Memory file restore. Use docmancer backup --dry-run for a read-only inventory only when backup scope is relevant. Create a snapshot, run docmancer restore, or approve a consolidation proposal only when the user explicitly authorizes that action. Cloud key rotation is unavailable while encrypted history exists. docmancer memory-restore is the legacy hash-guarded Shared Memory file operation.
When the user explicitly authorizes Personal Sync, use docmancer cloud connect for the first machine, four-word approval from a connected machine, and the automatic first transfer. Use docmancer cloud connect --recover only when no connected machine remains. docmancer cloud estimate is a read-only preview of upload size and plan limits. docmancer cloud sync is an explicit retry or later push and pull, not an onboarding requirement.
Documentation workflow
- Run
docmancer docs list. - Query an existing source with
docmancer docs query "". - If required documentation is absent and adding it is within the task, use
docmancer docs add. - Keep documentation results separate from memory results.
docmancer docs add ./docs
docmancer docs add https://docs.example.com
docmancer docs query "how to authenticate"
docmancer docs query "how to authenticate" --expand
docmancer docs query "how to authenticate" --expand page
docmancer docs query "how to authenticate" --format json
docmancer docs query "how to authenticate" --allow-degraded
docmancer docs list
docmancer docs sync
docmancer docs remove
docmancer docs download --output
docmancer doctor
Use docs add for both local documentation and URLs. Use root import only for Markdown intended for memory curation.
Generation providers
Configure credentials with docmancer providers key (prompt or stdin only), inspect readiness with docmancer providers list, and select defaults with docmancer providers set.
Supported generation providers: openrouter, openai, anthropic, google, mistral, groq, deepseek, xai, together, fireworks, cohere, openai-compat, ollama, lmstudio.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: docmancer
- Source: docmancer/docmancer
- License: MIT
- Homepage: https://docmancer.dev
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.