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.
npx skills add FlyFission/nuclear-grade-context-engineering --skill recording-what-an-agent-didgit clone --depth 1 https://github.com/FlyFission/nuclear-grade-context-engineeringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/flyfission/nuclear-grade-context-engineering/recording-what-an-agent-did)<a href="https://agentmods.dev/skills/flyfission/nuclear-grade-context-engineering/recording-what-an-agent-did"><img src="https://agentmods.dev/badge/skills/flyfission/nuclear-grade-context-engineering/recording-what-an-agent-did/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/flyfission/nuclear-grade-context-engineering/recording-what-an-agent-did"><img src="https://agentmods.dev/badge/skills/flyfission/nuclear-grade-context-engineering/recording-what-an-agent-did.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.01720 |
| Opus 5 | $0.00045 | $0.00860 |
| Sonnet 5 | $0.00018 | $0.00344 |
| Haiku 4.5 | $0.00009 | $0.00172 |
Grade A, and why
recording-what-an-agent-did 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recording What an Agent Did
Overview
A "does it work" check proves what an agent produced, not how it got there. Sometimes how it got there matters: for debugging, for auditing, for reviewing cost, or for defending a release decision. This skill says what to record about the run, how much detail to capture, and how to link it into the packet's trace.md and verification.md as evidence someone else could reproduce.
Decision contract
- Claim checked: every step that mattered -- tool call, edit, command, API call, approval -- has a recorded result and status, and each stayed inside the power
basis.mdgranted. - Artifact observed: the run log/transcript/trace export against
basis.mdandplan.md-> step-level trace rows, decision-point and approval records, and a token/delay summary intrace.md/verification.md, linked toship.md. - Decision affected: warn -- the step-level execution evidence the
ship.mddecision relies on. - Failure class: unevidenced-run (a stayed-in-scope claim with no step-level evidence, or unexplained cost).
- Next action: record the gap for
ship.md; a power breach or unexpected side effect escalates to pause/incident.
When to Use
- An agent ran tool calls that matter (file writes, API calls, command runs) and the packet needs evidence you can check.
- A release decision turns on whether the agent followed the plan, the scope, and its power limits.
- Token use, delay (latency), or cost is one of the things you have to verify for this change.
- A reviewer or auditor needs to rebuild what the agent did without reading a raw chat log.
- A review after an incident, or an OPEX review (a lessons-from-operation review), needs repeatable evidence of how the agent behaved.
When Not to Use
- The run was read-only exploring, with no real side effects and nothing riding on a release.
- The packet mode is Quick and the proof is one simple step that always gives the same answer.
- A full tracing platform already captures and exports this run data. Link to its output instead of copying it.
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.
- 11d ago First seen · 124 lines · 90 tokens per session scan A b5497c783e22
recording-what-an-agent-did is a skill published in the GitHub repository FlyFission/nuclear-grade-context-engineering (33 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,720 once invoked, about $0.0005 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.
Other skills, from other repositories
contextlock
Safely inspect a repository through the ContextLock MCP server. Use when exploring, searching, reviewing, or auditing repository files with ContextLock, especially before reading unfamiliar code or when sensitive files and secrets may be present.
nopus-simplify
Rewrite the immediately preceding assistant response with clearer and more direct prose when the user invokes this skill.
thumbgate-guard
Turn the agent's most recent mistake into an enforced ThumbGate prevention rule (a PreToolUse block gate) so the same bad tool call is intercepted before it runs again, in this and every future session across Claude Code, Cursor, Codex, Gemini, Amp, and Cline. Captures the failure with the capturefeedback MCP tool…
search-lessons
Search promoted lessons for corrective actions, lifecycle state, linked rules, and linked gates.
brpr
(devtools plugin) Create a branch, commit changes, push, and open a PR — or just commit+push+PR if already on a feature branch. Links related issues from GitHub or Linear based on project tracker config.
release
Automate the release process. Use when user says "cut a release", "new version", "bump version", "publish release", or anything about versioning and publishing.