hindsight-coding-agent

A guide to how this machine’s Hindsight memory works for coding-agent sessions. It explains automatic project memory, recalling past context, and saving session knowledge.

In plain words
What is it for?
Use it to understand per-repository memory, automatic session recall, saved conversations, configuration options, and common memory-related problems.
Why use it?
It helps explain where the agent’s project context comes from and how to configure or troubleshoot memory when it is missing or incorrect.

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/vectorize-io/hindsight/skill
Any agent
npx skills add vectorize-io/hindsight --skill skill
Clone the repo
git clone --depth 1 https://github.com/vectorize-io/hindsight

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,493 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 $0.00071 $0.06493
Opus 5 $0.00036 $0.03247
Sonnet 5 $0.00014 $0.01299
Haiku 4.5 $0.00007 $0.00649

Measured yesterday against content hash 00a5f7ec549e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hindsight-coding-agent 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 yesterday.

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.

hindsight-integrations/coding-agents/skill/SKILL.md · 416 lines

How it starts

The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hindsight Coding-Agent Memory

This machine runs the hindsight-coding-agents plugin: long-term project memory for coding sessions, backed by a Hindsight server. You (the agent) are already wired into it — this skill explains what happens automatically, which tools you have, and how to configure or debug it.

What happens automatically (no action needed)

  • Per-repo memory bank: each repository resolves to a bank (shown in the session banner: ↳ memory bank “coding-agent::<repo>”). Worktrees share the main repo's bank.
  • Ingestion builds itself: on first open, the bank is seeded from recent commit messages and a read-only codebase survey; every session start, a background engine tops it up (new commits, new conversations) and keeps 5 knowledge pages current. There is NO ingest command to run.
  • Session synthesis: by default, the first prompt of a session triggers one deep memory synthesis (reflect) injected into context. With autoReflect=false, the agent searches the knowledge pages first and reflects only when they are too shallow.
  • Write-back: the session transcript is retained into the bank automatically at session end (per-turn on opencode). The user never needs to "save" a conversation.

Storing things deliberately

When the user says "store this in hindsight" / "remember this":

  • The current conversation is captured automatically at session end — say so; no tool needed.
  • An external document, notes, or durable findingshindsight_ingest_document(title, content).
  • A new feature/initiative being startedhindsight_capture_initiative(title, summary), right after the plan is agreed and before code is written.
  • A plan that materially changed (goal, scope, or rationale — including mid-implementation) → call hindsight_capture_initiative again with relates_to_page_id set to that initiative's page id, summarising the current intent. Same page, updated plan — never a second page. Trivial course-corrections don't count.

Read the full file on GitHub · 416 lines

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. yesterday First seen · 416 lines · 71 tokens per session scan A 00a5f7ec549e

Subscribe to this mod's changes

hindsight-coding-agent is a skill published in the GitHub repository vectorize-io/hindsight (21,822 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 6,493 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

nocturnusai-admin

Use when managing NocturnusAI databases, tenants, health checks, metrics, backups, API key management, RBAC configuration, admin operations, or operational monitoring. Triggers on: NocturnusAI database, tenant, health, metrics, backup, API key, RBAC, admin, monitoring, operational.

Auctalis/nocturnusai · 72 tokens

nocturnusai-connect

Use when setting up NocturnusAI connection, configuring MCP server in claudedesktopconfig.json or .mcp.json, setting up API keys, auth, RBAC bootstrap, creating databases/tenants, or troubleshooting connection issues. Triggers on: setup, connect, configure, MCP, auth, API key, tenant, database, bootstrap, NocturnusAI.

Auctalis/nocturnusai · 85 tokens

nocturnusai-knowledge

Use when working with NocturnusAI facts and rules — asserting (tell), querying (ask/infer), teaching rules (teach), retracting (forget), bulk operations, aggregation, or discovering predicates. Covers the core knowledge base CRUD operations. Triggers on: tell, ask, teach, forget, assert, query, infer, rule, fact…

Auctalis/nocturnusai · 92 tokens

nocturnusai-memory

Use when working with NocturnusAI agent memory — context windows, salience scoring, temporal queries, recall, consolidation, decay, TTL, expiration, event streaming, or memory lifecycle management. Triggers on: memory, context window, salience, temporal, recall, consolidate, decay, TTL, expire, events, NocturnusAI…

Auctalis/nocturnusai · 81 tokens

nocturnusai-reasoning

Use when working with NocturnusAI advanced reasoning — negation-as-failure (NAF), scopes (fork/merge/diff), hypothetical reasoning, confidence scores, conflict resolution strategies, or proof chains. Triggers on: NAF, negation, negation-as-failure, scope, fork, merge, hypothesis, confidence, conflict, proof, what-if…

Auctalis/nocturnusai · 92 tokens

agent-release-manager

Agent skill for release-manager - invoke with $agent-release-manager.

ruvnet/ruflo · 16 tokens