Agentpack

Repo-native task continuity for AI coding agents: a reviewed task-state ledger served.

Connector by ihorponom · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 18

Chalk Labs

Need help deploying Agentpack?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/ihorponom-agentpack

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Repo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP.

Use cases: agent-memory, project-management

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools: 13 read · 6 write · 8 delete
Secrets: None asked for
Install scripts: None found
Runs as: Node.js package

Tools by what they do 27

Read from the source code; the running server may list different tools.

Read 13 · Look things up without changing anything.

bundle_import_plan
bundle_inspect
diff
load_context
release_preflight
replay
resume
source_status
task_audit
task_handoff
task_list
task_status

Show 1 more tools

usage_report

Write 6 · Create, change, send or run things.

attach_evidence
bundle_export
bundle_import
record_dead_end
record_decision
task_start

Delete 8 · Delete, drop, revoke or wipe things.

checkpoint
record_source
task_finalize
task_park
task_switch
task_update
task_update_verification
usage_link

Network hosts it talks to 2

github.com · found in code
glama.ai · found in code

Files it touches

Your home directory (~)
Any path the agent passes to its tools

Tools (27)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

attach_evidence
Store verification output (test results, command output, review findings, notes, or links) as a file under .agentpack/evidence/ plus a ledger event, returning an evidence id to reference from task_update_verification, task_finalize, or record_decision. Call for meaningful verification worth preserving; for small tasks prefer one aggregated evidence item over many per-command items. Provide the body inline via content or from a file via path.
bundle_export
Export one Task Passport, compact handoff, latest task checkpoint when available, selected source conclusions, and optionally referenced evidence to a redacted agentpack.task-bundle JSON file. Writes only the new bundle file at outputPath; pack state is unchanged.
bundle_import
Import a task bundle into this pack. By default it only returns the read-only import plan; nothing is written unless write is true. A write import runs under a pack lock, creates a parked task with local verification reset to unknown, retains the bundle and an import manifest, and never changes the current-task pointer. Inspect or plan untrusted bundles first.
bundle_import_planread-only
Plan a task bundle import against this pack without writing anything: returns create, idempotent, or conflict actions with an explicit read-only guarantee. Call to preview exactly what bundle_import with write: true would do.
bundle_inspectread-only
Validate and summarize an untrusted task bundle file: schema and digest status, origin, included records, and warnings. Read-only — never writes pack state. Call before planning or applying an import of a bundle you did not produce.
checkpointcan change or delete data
Save a durable progress checkpoint under .agentpack/checkpoints, capturing summary, git state (branch, commit, diff) and the current task id when that task is active, blocked or verifying, and updating the pack-level status and next actions that seed the next session's load_context. Call after meaningful progress, before ending a session, or before risky changes — not after every small step.
diffread-only
Compare two checkpoints, showing their summaries, status lines, and git refs side by side. Defaults to comparing the previous checkpoint against the latest. Call to see what changed between sessions. Read-only.
load_contextread-only
Load a token-budgeted markdown resume of Agentpack state for the current task: Task Passport status and next actions, git state, query-relevant decisions, dead ends, and source conclusions, plus gate warnings when the task lifecycle needs attention. Call once at the start of a session or task, before reading code; re-call only for a different query or budget. Read-only.
record_dead_end
Record an approach that failed so future agents do not repeat it. Call when an attempted direction is abandoned for a durable reason, not for ordinary debugging iterations. Writes one event under .agentpack/; secret-like values are redacted.
record_decision
Append a durable technical or product decision to the Agentpack ledger so future sessions inherit it. Call for decisions that matter beyond this session (architecture, contracts, tradeoffs), not for routine preferences or per-edit narration. Writes one event under .agentpack/; secret-like values are redacted.
record_sourcecan change or delete data
Record a durable conclusion about a source file in the Source Cache: stores the file's current content hash with your summary so future sessions can reuse the conclusion until the file changes. Call after inspecting an important file when the conclusion is reusable; do not record every file read, and re-record only when the conclusion itself changed. Writes under .agentpack/.
release_preflightread-only
Report local release readiness: release metadata, Trusted Publisher wiring, and the manual release-prep commands. Read-only — never pushes, tags, publishes, or creates GitHub Releases. Call when preparing a release, not during routine work.
replayread-only
Print a chronological timeline of recent Agentpack ledger events (decisions, dead ends, evidence, source records, checkpoints, task events), one line per event with timestamp and type. Call to audit how the task history unfolded when a resume is not enough; not part of the routine load_context/checkpoint loop. Read-only.
resumeread-only
Generate the same token-budgeted markdown resume as load_context: Task Passport state, git state, query-relevant records, and gate warnings. Prefer load_context at task start; use resume for ad-hoc re-reads with a different query or budget mid-session. Read-only.
source_statusread-only
Check whether recorded source conclusions are unchanged, changed, or missing by re-hashing the files; use changed/missing filters for stale source-cache triage. Call when you need a full stale-source check beyond what load_context already showed; do not repeat it when a recent load_context, task_audit, or status check answered the question. Read-only.

Show 12 more tools

task_auditread-only
Audit the current Task Passport for continuity risks and advisory-only risk-proportional adversarial-verification evidence (a concise verification note or test output at low risk; independent read-only review and a named disconfirming check at medium/high risk). It does not judge semantic correctness or block lifecycle actions. Call before finalizing, after a long gap, or when drift is suspected; skip when a recent audit already answered it. Read-only.
task_finalizecan change or delete data
Close the current Task Passport. Requires verification to already be passed, failed, or accepted, or that final status passed explicitly via status. Use task_park for deferred work instead of closing it; accepted finalization with remaining next actions requires force. Returns non-blocking hygiene and adversarial-verification advisories only; it never judges semantic correctness or blocks completion.
task_handoffread-only
Generate a compact handoff for the current Task Passport — objective, constraints, write scope, next actions, verification, latest task checkpoint when available, drift, and audit summary — so another chat, client, worktree, or agent can continue the work. Call before switching contexts. Read-only.
task_listread-only
Find Task Passport ids or inspect task history. Without status lists open tasks; pass all: true for full history. compact and limit shorten the result. Filters combine with AND; current task is marked with an asterisk. Read-only.
task_parkcan change or delete data
Mark the current Task Passport parked so unrelated work can start without finalizing it. Use for intentionally deferred work: parking preserves verification state and the task can be resumed later with task_switch. Do not park to skip verification of finished work; use task_finalize to close it instead.
task_start
Create a new Task Passport and make it current, persisting it under .agentpack/. Call when starting a coherent phase of work and no task is active; it refuses to replace an active, blocked, or verifying current task — park or finalize that task first. Declare writeScope so the task gate can protect the task's boundaries.
task_statusread-only
Print a compact current-task state line by default; pass full: true for the detailed current view, or id to inspect a selected Passport with objective, constraints, all next actions and verification without switching tasks. Gate warnings always concern the actual current task. No source-cache scan; use task_audit for the full continuity audit. Read-only.
task_switchcan change or delete data
Make another open Task Passport current by id. Set parkCurrent: true to park a different active/blocked/verifying current task in the same locked transaction, after validating the target. Otherwise park or finalize it first. A parked target with pending or unknown verification resumes as active; a parked target with a final verdict resumes as verifying and stays frozen until verification returns to pending. Closed targets cannot be switched to.
task_updatecan change or delete data
Patch the current Task Passport without changing lifecycle status. List fields (constraints, writeScope, nextActions, tags) append and deduplicate; repositories upsert by id; omitted fields are preserved; empty or no-op updates fail. Pass clearNextActions to replace the next-actions list instead of appending, e.g. to clear a stale plan before finalizing. Pass replaceConstraints to replace constraints that are obsolete or superseded; removed constraints stay in the task history.
task_update_verificationcan change or delete data
Update the current Task Passport verification state. A final verdict (passed, failed, or accepted) moves the task lifecycle to verifying; pending or unknown returns it to active. Call after attach_evidence so the verdict is evidence-backed; identical repeated calls are no-ops.
usage_linkcan change or delete data
Link Codex/Claude Code session transcripts to a Task Passport so usage_report can report the task by id. Without pick, file, remove or coverage it only lists candidate sessions of the task worktree with requests while the task was current. Show candidates to the user and link only what they confirm: pick links sessions by session id (numbers can shift between calls); client/file/turns links an explicit one. Re-linking a file replaces its selection; remove unlinks a linked file by path or session id (traced sessions are always included). Writes .agentpack/usage/<task id>.json only.
usage_reportread-only
Report local Codex/Claude Code usage when the user asks about work usage. Pass task (Task Passport id; omit for the current task) to report the sources linked to it; sessions that ran Agentpack for the task (and their subagents) are included automatically; if none are traced or linked, the result lists candidate sessions of the task worktree to link with usage_link. Task reports count only requests made while the task was the current Passport; a subagent counts whole for the task current when it started. Alternatively supply manifest, or client/files for a direct report. Same read-only report …

Signals

Stars: 18
Forks: 1
Open issues: 0
Last commit: Oct 17, 2026 (13 days ago)
Last release: Oct 25, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name: io.github.ihorponom/agentpack
Version: 1.11.1
Auth: No auth
Packages: npm agentpack-cli
License: MIT
Repository: github.com/ihorponom/agentpack
First seen: Oct 24, 2026
Last checked: Oct 26, 2026
Source: Official MCP Registry github-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get Agentpack running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying Agentpack?

Call Get help

Cite this page

Agentpack MCP server. Agent Mart. https://agentmart.dev/connectors/ihorponom-agentpack (last updated 2026-10-26)