Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Effect Ledger

ASecurity

Record an effect, sign an effect, reconcile an effect or check "did this PR merge" through the signed AIWG effect ledger, using one aiwg effect command with scriptable exit codes

212 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsbashgit

Works with

cli

Security Analysis

A100/100

Scanned 9/27/2026

$npx -y skills add jmagly/aiwg --skill effect-ledger --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Effect Ledger?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Effect Ledger
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jmagly-effect-ledger-441e7ca6/badge)](https://www.skillsdirectory.com/skills/jmagly-effect-ledger-441e7ca6)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
namespace: aiwg
name: effect-ledger
platforms: [all]
description: Record an effect, sign an effect, reconcile an effect or check "did this PR merge" through the signed AIWG effect ledger, using one aiwg effect command with scriptable exit codes
---

# Effect Ledger

Record and reconcile side effects (tracker comments, PR merges, issue closes,
git commits and tags, files, decision receipts) in the signed AIWG effect
ledger with the `aiwg effect` CLI. The ledger proves what AIWG recorded and
what a verifier observed. It never authorizes an effect and never replays one:
an operator decision authorizes, the ledger proves.

## Triggers

- "record an effect" → `aiwg effect record`
- "sign an effect" → `aiwg effect record` (signed intent and completed)
- "reconcile effect" → `aiwg effect reconcile`
- "did this PR merge" → `aiwg effect reconcile --kind tracker.pr.merged`, or
  `aiwg effect probe --kind tracker.pr.merged --target gitea:owner/repo#34`
  when no merge intent was recorded (read-only, writes nothing)
- "did we already post this comment" → `aiwg effect lookup` before posting
- "verify the effect ledger" → `aiwg effect verify` (add
  `--with-decisions <audit.jsonl>` to check #1567 operator-decision links)
- "the effect ledger lock is stuck" → `aiwg effect recover-lock` (operator only)

## When to record

Record every externally visible effect that a retry or a crash could repeat:
cycle and closing comments, merges, issue closes, tags, release files, and
decision receipts. Do not record read-only queries.

## Process

1. **Name the effect.** Pick the kind and target, and the causal context that
   makes it unique. For a cycle comment:
   `--kind tracker.comment --target gitea:owner/repo#12 --issue 12 --action cycle-comment --cycle 1`.
   `aiwg effect id <identity>` prints the effect ID.
2. **Check before acting.** Run `aiwg effect lookup <identity>`. Exit 0 means
   the effect is already present: do not repeat it. Exit 4 means an earlier
   attempt has no outcome: run `aiwg effect reconcile` first.
3. **Carry the ID into the target** wherever the target allows it: a hidden
   `<!-- aiwg-effect: <effect-id> -->` line in a comment body, or an
   `Effect-Id: <effect-id>` git trailer. Verifiers use the marker to prove the
   effect happened.
4. **Perform the effect**, then record and sign it in one call:

   ```bash
   aiwg effect record --kind tracker.comment --target gitea:owner/repo#12 \
     --issue 12 --action cycle-comment --cycle 1 --payload-file comment.md
   ```

   `record` writes the signed intent, runs the kind's verifier, and appends
   `completed` when the verifier reports `present`. Repeating it with the same
   payload exits 0 with `"idempotent":true`. Use `--unverified` only when no
   verifier can see the target, and say so in your report.
5. **Reconcile uncertain effects.** `aiwg effect reconcile <effect-id>` (or the
   same identity flags) asks the verifier again and appends a `reconciled`
   record each time. For "did this PR merge", once the merge intent is
   recorded: `aiwg effect reconcile --kind tracker.pr.merged --target gitea:owner/repo#34`.
   Reconciling an effect with no recorded intent is a usage error (exit 2);
   record the intent first with `aiwg effect intent` or `aiwg effect record`,
   or use `aiwg effect probe <identity>` for an ad-hoc check that records
   nothing (same exit codes 0, 3 and 4).
6. **Link the authorizing decision** when an operator approved the effect:
   `--link operatorDecisionEventId=sha256:<hex>` (and
   `operatorDecisionRecordHash`) on `intent` or `record`.

## Exit codes

| Code | Meaning | What to do |
|---|---|---|
| 0 | present or recorded | Continue |
| 3 | absent | The target does not show the effect. Do not assume it is safe to replay; follow the workflow's own policy |
| 4 | unknown | Stop and escalate. Never replay on unknown |
| 5 | conflict | The same effect ID was recorded with a different payload. Stop |
| 6 | integrity failure | The ledger failed verification. Stop and report |
| 2 / 1 / 7 | usage / internal / artifact root unavailable | Fix the command or the artifact root; nothing was written |

## Rules

- Output is JSON by default and every document has a `schema` member; add
  `--format text` only for people.
- Never pass raw bodies, secrets or tokens as flags. Payloads are digested from
  `--payload-file` or given as `--payload-digest`.
- The ledger key lives in the host secret service. `aiwg effect keys list`
  shows key IDs and public keys only; `keys init` and `keys rotate` are
  operator actions.
- `aiwg effect recover-lock --lock <name> --authorize` is an operator action.
  It refuses live, reused or unverifiable lock owners and records the recovery
  in the ledger. Never run it without the operator's explicit approval.

## References

- @$AIWG_ROOT/docs/contracts/effect-ledger.v1.md — contract, exit codes and verifier rules
- @$AIWG_ROOT/docs/cli/reference.md — `aiwg effect` command reference

Attribution

jmaglyjmagly
View sourceSee grades on GitHubMore from jmagly →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →