intent-writeback

A post-implementation recording tool that captures lessons learned while building an exported work packet and proposes updates to the project’s planning documents.

In plain words
What is it for?
Use it to record implementation learnings, approve or reject planning changes, close a completed packet, and archive its finished record.
Why use it?
It preserves discoveries from implementation without directly rewriting the agreed goals or rules. Only items the user approves are promoted into those documents.

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/ijust/intent-planner/intent-writeback
Any agent
npx skills add ijust/intent-planner --skill intent-writeback
Clone the repo
git clone --depth 1 https://github.com/ijust/intent-planner

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,704 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 $0.00055 $0.03704
Opus 5 $0.00028 $0.01852
Sonnet 5 $0.00011 $0.00741
Haiku 4.5 $0.00006 $0.00370

Measured 2d ago against content hash fe03bcd7e347, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intent-writeback 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.

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.

templates/en/claude/skills/intent-writeback/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

intent-writeback Skill

Core Mission

  • Success Criteria:
    • The target packet is identified as exactly one via the 5-tier priority (argument → latest row of export-log → Source Packet heading → direct-implementation route [explicit exit record format=direct primary, 3-condition AND inference fallback] → text matching + confirmation)
    • Learnings from the 5 perspectives are extracted and presented by cross-checking the implementation reality against the packet definition and the compass
    • The learnings are first recorded into deltas.md as a delta, and the canonical deliverables are not edited directly
    • Only the approved items are reflected into the canonical deliverables, with Status and reflection targets recorded in the delta
    • Declined items carry one of the two tags "rejected (no re-proposal) | on-hold (re-propose at the next writeback)"
    • The completed packet has state: done, closed_at, and spec_refs filled in, has been moved to archive//, and index.md has been regenerated
    • The outcome branch is selected only when the user explicitly says "outcome learning", and recording its pending observation does not run Packet completion processing
    • No application code has been changed at all

Execution Steps

Step 0: Determine the operation kind

  • Select the outcome branch only when the user explicitly says "outcome learning." If ordinary implementation learning versus outcome recording is ambiguous, confirm the operation kind in plain words and wait for the answer (rules §0).

Step 1: Identify the target packet

  • Read rules/writeback-protocol.md and identify exactly one target via the 5-tier priority (1. argument → 2. packet name in the latest row of export-log.md (canonical) → 3. "## Source Packet" heading in the selected exit's drafts (only when exactly one packet directory exists) → 4. direct-implementation route [for cases that bypass cc-sdd / openspec / speckit: use the explicit exit record format=direct as the primary signal, else fall back to the 3-condition AND inference of spec_refs empty + no export-log row + state=done and uniquify by name matching] → 5. text matching + user confirmation). When a fallback (tier 3 or later) identified the target, announce that fact; if the target still cannot be identified, ask for a specification and stop (see rules).
  • Identify the target packet's file by matching name in index.md / under active/ of .intent/packets/. If it is not under active/, refer to archive/ explicitly to identify it and report the fact that the packet is done / superseded (the only explicit exception to the principle of normally never reading archive/; see rules).
  • Read .intent/mode.md. If absent, continue with the standard default and announce it.
  • Present the list of past delta entries of the target packet (including declined items with the "on-hold" tag). Writing back the same packet again creates a new entry (see rules).
  • In the outcome branch, identify the target L1 by a verbatim quote. If the same quote occurs more than once, show the candidates and wait for the user's selection (rules §1.5).

Read the full file on GitHub · 98 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 · 98 lines · 55 tokens per session scan A fe03bcd7e347

Subscribe to this mod's changes

intent-writeback is a skill published in the GitHub repository ijust/intent-planner (5 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 3,704 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.